Vai al contenuto principale della pagina

Sentimental Analysis and Deep Learning : Proceedings of ICSADL 2021



(Visualizza in formato marc)    (Visualizza in BIBFRAME)

Autore: Shakya Subarna Visualizza persona
Titolo: Sentimental Analysis and Deep Learning : Proceedings of ICSADL 2021 Visualizza cluster
Pubblicazione: Singapore : , : Springer Singapore Pte. Limited, , 2021
©2022
Descrizione fisica: 1 online resource (1023 pages)
Soggetto genere / forma: Electronic books.
Altri autori: BalasValentina Emilia  
KamolphiwongSinchai  
DuKe-Lin  
Nota di contenuto: Intro -- 508480_1_En_BookFrontmatter_OnlinePDF -- Preface -- Acknowledgments -- Contents -- Editors and Contributors -- Analysis of Healthcare Industry Using Machine Learning Approach: A Case Study in Bengaluru Region -- 1 Introduction -- 2 Literature Survey -- 3 Challenges Faced During Data Acquisition -- 4 Methodology -- 4.1 Web Scraping -- 4.2 Statistical Analysis -- 4.3 Natural Language Processing -- 4.4 Sentimental Analysis -- 5 Results and Discussion -- 6 Conclusion -- References -- Dynamic Document Localization for Efficient Mining -- 1 Introduction -- 2 Literature Review -- 3 Methodology -- 3.1 Probabilistic Model for Query-Workload -- 3.2 Probabilistic Model for Content-Workload -- 3.3 Bernoulli Model for Rank Calculation -- 4 Fuzzy Threshold Algorithms -- 5 Experimental Analysis -- 5.1 Effect of Attribute Suggestion to Determine Precision and Recall -- 5.2 Effect of Biasing Coefficient for Determining Attribute Matches -- 5.3 Effect of Database Size for Determining Precision -- 6 Conclusion -- References -- SentiSeries: A Trilogy of Customer Reviews, Sentiment Analysis and Time Series -- 1 Introduction -- 2 Literature Review -- 3 Theory of Dynamic Sentiment Tracking -- 3.1 Natural Language Processing-Sentiment Analysis -- 3.2 Time Series Characteristics -- 4 Dataset -- 5 Results and Discussions -- 6 Conclusions and Future Work -- References -- Video Summarization Using Fully Convolutional Residual Dense Network -- 1 Introduction -- 2 Related Work -- 3 Our Approach -- 3.1 Problem Description -- 3.2 Fully Convolutional Residual Dense Network -- 4 Results -- 4.1 Datasets -- 4.2 Result -- 5 Conclusion -- References -- An Efficient Deep Learning Approach for Detecting Pneumonia Using the Convolutional Neural Network -- 1 Introduction -- 2 Literature Review -- 3 Material and Methods -- 3.1 Dataset -- 3.2 Preprocessing and Data Augmentation.
3.3 Proposed Model -- 4 Result Analysis -- 5 Discussion -- 6 Conclusion -- References -- QMCDS: Quantum Memory for Cloud Data Storage -- 1 Introduction -- 2 Literature Survey -- 2.1 Related Work -- 2.2 Contributions -- 3 Preliminaries -- 3.1 Qubit -- 3.2 Representation of Quantum Gates -- 3.3 Bloch Sphere -- 4 Proposed Solution -- 5 Experiments and Observation -- 6 Conclusion and Future Scope -- References -- A Study Towards Bangla Fake News Detection Using Machine Learning and Deep Learning -- 1 Introduction -- 2 Related Works -- 3 Proposed Research Methodology (PRM) -- 3.1 Experimental Setup -- 3.2 Data Preparation Pipeline (DPP) -- 3.3 Features Extraction Methods (FEM) -- 3.4 Algorithm Selection Procedure (ASP) -- 4 Result and Analysis -- 4.1 Performance Analysis (PA) -- 4.2 Comparative Analysis (CA) -- 5 Conclusions and Future Work -- References -- A Deep Learning Approach to Analyze the Propagation of Pandemic in America -- 1 Introduction -- 1.1 The Goal of the Paper and Its Contributions -- 1.2 Organization -- 2 The Architecture of the Framework -- 3 Proposed SIR Model -- 4 Proposed Algorithm -- 5 Performance Evaluation -- 5.1 Results -- 6 Discussion -- 7 Conclusion and Future Research -- References -- Graph Convolution-Based Joint Learning of Rumor with Content, User Credibility, Propagation Context, and Cognitive as Well as Emotion Signals -- 1 Introduction -- 2 Existing Work -- 2.1 Rumor Detection and Veracity Classification -- 2.2 Emotion Research and Application of Emotion in Fake News and Rumor Research -- 2.3 Cognitive Signals in Disinformation Research -- 3 Dataset -- 4 Analysis of Cognitive and Emotion Patterns in Rumor and Non-rumor -- 5 Methodology -- 6 Results and Analysis -- 7 Conclusion and Future Work -- References -- Deep Learning-Based Real-Time Object Classification and Recognition Using Supervised Learning Approach.
1 Introduction -- 2 Literature Survey -- 3 Proposed System -- 4 Results and Analysis -- 4.1 Performance Analysis [15-19] -- 5 Conclusion and Future Work -- References -- Single-Channel Speech Enhancement in Modulation Domain Using Particle Swarm Optimization -- 1 Introduction -- 2 Spectral Subtraction -- 2.1 Modulation Domain Spectral Subtraction -- 3 Standard Particle Swarm Optimization -- 4 Proposed Noise Estimation Using PSO -- 5 Results -- 6 Conclusion -- References -- Pneumonia and Diabetic Retinopathy Detection Using Deep Learning Algorithm -- 1 Introduction -- 2 Related Work -- 3 Research Gap -- 4 Problem Definition -- 5 Methodology -- 5.1 Algorithm Used- Convolutional Neural Networks -- 5.2 Data Pre-processing -- 5.3 Model Information -- 5.4 Datasets Used -- 6 Results -- 6.1 Screenshots of Results -- 7 Conclusion -- 8 Future Scope -- References -- Design of IoT-Based Improved Multimodal Ant Colony Optimızation (MM-ACO) Algorithm for Real-Time Applications -- 1 Introduction -- 2 Existing System -- 3 Proposed Algorithm -- 4 Conclusion -- References -- An Interview Transcriber Using Natural Language Processing -- 1 Introduction -- 2 Literature Review -- 3 Proposed System Methodology -- 4 Information Extraction -- 4.1 Approaches to Extract Information -- 5 Textual Similarity -- 5.1 Approaches for Text Pre-processing -- 6 Observed Results -- 6.1 Extracting Information Using Keywords -- 6.2 Extracting Information Based on Similar Pool of Words -- 7 Work Embeddings for Future Deeper Approaches Like Word2Vec -- 7.1 Word2Vec -- 8 Conclusion and Future Scope -- References -- Plagiarism Detection for Source Codes and Texts -- 1 Introduction -- 2 Objectives -- 3 Literature Review -- 4 Proposed Work -- 5 Experimental Analysis -- 6 Result and Discussion -- 7 Conclusion -- References.
Investigation of Kinetic Energy Harvesting from Human Body Motion Activities Using Free/Impact Electromagnetic Generator -- 1 Introduction -- 2 Literature Review -- 3 Methodology -- 3.1 Storage of Harvested Energy -- 3.2 The Designed Structure of Biomechanical Hip Energy Harvester -- 4 Results and Discussion -- 4.1 Hip Joint Gait Cycle -- 4.2 Positioning the Angle of Harvester -- 4.3 Hip Joint Gait Harvesting at Walking Speed 80 M/Min -- 5 Conclusion -- References -- Automated Determination of Critical Temperature -- 1 Introduction -- 1.1 Critical Temperature -- 1.2 Machine Learning Algorithms -- 1.3 Dataset -- 2 Literature Survey -- 3 Methodology -- 3.1 Algorithm Followed for Developing the Models -- 3.2 Data Preprocessing -- 3.3 Working of the Models -- 3.4 Model Training -- 3.5 Model Testing -- 3.6 Model Performance Determination -- 4 Results and Discussion -- 5 Conclusion -- References -- ANN-based Hybridization Approach for Detection of Cardiac Disease -- 1 Introduction -- 1.1 Feedforward Networks (FFN) -- 1.2 Feedback Networks -- 1.3 ANN Learning -- 2 Literature Review -- 3 Problem Formulation -- 4 Proposed System -- 5 Algorithms -- 5.1 Artificial Neural Network (ANN) -- 5.2 Gradient Descent Algorithm -- 5.3 Genetic Algorithm -- 6 Error Back Propagation (EBP) -- 7 Machine Learning Network -- 8 Benefits of Genetic Algorithm in Neural Network -- 9 Tests and Results -- 10 Conclusion and Future Scope -- References -- The Implementation of Enhanced K-Strange Points Clustering Method in Classifying Undergraduate Thesis Titles -- 1 Introduction -- 1.1 Motivation -- 2 Illustration of Enhanced K-Strange Points Clustering Algorithm -- 3 Research Method -- 3.1 Research Data -- 3.2 Text Mining -- 3.3 Enhanced K-Strange Points Clustering Algorithm -- 3.4 Silhouette Coefficient Testing -- 4 Mathematical Illustration.
4.1 Step I: Finding the Minimum of the Dataset (Kmin) -- 4.2 Step II: Finding the Maximum of the Dataset (Kmax) -- 4.3 Step III: Finding the Third Strange Point -- 4.4 Step IV: Correcting the K-Strange Point -- 4.5 Step V: Assigning Points to Respective Clusters -- 5 Result and Discussion -- 5.1 Collect Data -- 5.2 Text Parsing -- 5.3 The Process of Document Clustering -- 5.4 Testing -- 6 Conclusion -- References -- Spam Email Detection Using Machine Learning and Neural Networks -- 1 Introduction -- 2 Literature Review -- 2.1 Existing System -- 3 Proposed Methodology -- 3.1 Data Set Reading and Inspection -- 3.2 Text Preprocessing -- 3.3 Feature Sets and Vectorization -- 3.4 Pipeline and Modeling -- 4 Results -- 5 Conclusion -- References -- Online Appointment Management System in Hospitals Using Distributed Resource Allocation Algorithm -- 1 Introduction -- 2 Literature Survey -- 3 Proposed System -- 3.1 Module Description -- 3.2 Distributed Resource Allocation Algorithm -- 3.3 Data Flow -- 4 Experimental Result -- 5 Conclusion -- References -- BeFit-A Real-Time Workout Analyzer -- 1 Introduction -- 2 Related Work -- 3 Methodology Adopted -- 3.1 Working of PoseNet Model -- 3.2 Comparison Analysis -- 3.3 Detecting User's Pose -- 3.4 Getting Pose from Yoga/Gym Workout Selected -- 3.5 Comparing the Skeletons -- 3.6 Data Stream Handling -- 4 Final Implementation -- 5 Advantages -- 6 Future Scope -- 7 Results -- 8 Conclusion -- References -- Analysis of Car Damage for Personal Auto Claim Using CNN -- 1 Introduction -- 2 Literature Survey -- 3 Design -- 4 Proposed Method -- 5 Results and Simulation -- 6 Conclusion -- References -- On the Analysis Problem of the Attribute-Based Access Control Model HGABAC -- 1 Introduction -- 2 HGABAC: An ABAC Model and Its Administrative Model GRUAG -- 3 Automated Analysis Technique for GURAG System -- 4 Evaluation.
5 Conclusions.
Titolo autorizzato: Sentimental Analysis and Deep Learning  Visualizza cluster
ISBN: 981-16-5157-4
Formato: Materiale a stampa
Livello bibliografico Monografia
Lingua di pubblicazione: Inglese
Record Nr.: 9910506400703321
Lo trovi qui: Univ. Federico II
Opac: Controlla la disponibilità qui
Serie: Advances in Intelligent Systems and Computing Ser.