book

Hybrid Information Systems

Name: Hybrid Information Systems
ISBN: 9783111331188

by Ramakant Bhardwaj, Pushan Kumar Dutta, Pethuru Raj, Abhishek Kumar, Kavita Saini, Alfonso González Briones, Mohammed K.A. Kaabar

July 2024

Intermediate to advanced

518 pages

18h 9m

English

De Gruyter

Read now

Unlock full access

Contributing authors
Bhupinder Singh, Pushan Kumar Dutta, Christian Kaunert Synchronizing neural networks, machine learning for medical diagnosis, and patient representation: looping advanced optimization strategies assisting experts for complex mechanisms behind health and disease detection
1 Introduction1.1 Significance of medical diagnosis1.2 Role of machine learning in healthcare1.3 Need for synchronized neural networks and advanced optimization strategies in healthcare1.4 Research objectives1.5 Contributions of the paper2 Synchronizing neural networks: medical diagnosis2.1 Use of neural networks in synchronizing data3 Machine learning for medical diagnosis: aid in medical diagnosis and datasheet4 Patient representation: electronic health records (EHRs)5 Looping advanced optimization strategies behind health and disease detection6 Complex mechanisms behind health and disease detection7 Conclusion and future scopeAssignment questions
Upinder Kaur The future of predictive health: evaluating the role of neural network based hybrid models in healthcare
1 Introduction2 Background and literature3 Neural networks in healthcare3.1 Traditional neural networks3.2 Hybrid models in healthcare4 Evaluation of the neural network-based hybrid models5 Case study: disease prediction workflow5.1 Module 1: data collection – gathering the mosaic of health indicators5.2 Module 2: data analysis – deciphering the health tale through advanced analytics5.3 Module 3: model and prediction – crafting the predictive saga6 Open issues and challenges: detailed exploration6.1 Data privacy and security6.2 Integration with healthcare systems6.3 Technical limitations and resource constraints6.4 Ethical and societal considerations6.5 Ongoing research and development needs7 Conclusion
Kirti Verma, Vineeta Shrivastava, Neeraj Chandnani, M. Sundararajan, Adarsh Mangal An overview of new trends on deep learning models for diabetes risk prediction
1 Introduction2 Background machine learning and deep learning3 Systematic literature review4 Proposed methodology4.1 Preprocessing the dataset4.2 Structure and drill the Deep Learning for Predicting Diabetes (DLPD) model4.3 Overexcited limit change5 Results and discussion6 ConclusionAssignment questions
Vinit Kumar, Prabhjot Kaur, Sukhpreet Kaur A study on the detection and diagnosis of cervical cancer using machine and deep learning models
1 Introduction1.1 Key features2 Framework3 Background4 Analysis5 ConclusionAssignment questions
Umang Garg, Rahul Singh Pundir, Mahesh Manchanda, Neha Gupta, Ram Bhawan Singh Sentiments and opinions shared on social media during the COVID-19 pandemic using machine learning techniques
1 Introduction1.1 Impact of COVID1.2 Social media in COVID2 Sentiment analysis2.1 Key features2.2 Dataset2.3 Preprocessing of data3 Model selection and extraction3.1 Tokenizing and encoding the data3.2 Splitting the data4 Model selection and extraction4.1 Layer of input4.2 Secret layer4.3 Layer of embedding4.4 Bidirectional LSTM4.5 Layer of output4.6 Function of loss4.7 Testing5 Methodology and results5.1 Working of LSTM6 ConclusionAssignment questions
Pooja Dixit, Kusumlata Gehlot Combining decision tree and Bayesian networks for improved predictive analytics
1 Introduction1.1 The significance of predictive analytics1.2 Decision trees in predictive analytics1.3 BNs in predictive analytics1.4 The Bayesian network1.5 The research problem1.6 Goals of the research1.7 Chapter structure2 Literature review3 Methodology3.1 Data collection, preprocessing, and feature selection3.2 Integration of decision trees and BNs3.3 Tools and software4 Significance of using BNs and decision trees together in predictive analytics5 Result analysis5.1 Model accuracy for customer churn and stock price prediction6 ConclusionAssignment questions
Sakshi, Tushar Mehrotra, Priyanka Tyagi, Vishal Jain Emerging trends in hybrid information systems modeling in artificial intelligence
1 Introduction to hybrid information systems in artificial intelligence1.1 Definition and overview of hybrid information systems1.2 Importance and benefits of hybrid approaches in AI2 The integration of deep learning and symbolic reasoning2.1 Combining neural networks and rule-based systems2.2 Challenges in integrating deep learning and symbolic reasoning3 Ensemble methods in hybrid AI systems3.1 Leveraging ensemble learning for improved performance3.2 Ensemble techniques for addressing uncertainty and bias4 Reinforcement learning and expert systems fusion4.1 Integrating reinforcement learning with knowledge-based systems4.2 Challenges in combining reinforcement learning and expert systems5 Hybrid AI in natural language processing5.1 Hybrid models for language understanding and generation5.2 Challenges in achieving seamless NLP integration in hybrid systems6 Hybrid approaches in computer vision6.1 Combining deep learning and traditional computer vision techniques6.2 Overcoming limitations and ambiguities in hybrid computer vision systems7 Explainable AI in hybrid information systems7.1 Ensuring transparency and interpretability in hybrid models7.2 Research scope7.3 Future challenges7.4 Interpreting and communicating the results of hybrid AI systems8 Edge computing and hybrid AI systems8.1 Edge computing8.2 Hybrid AI systems8.3 Advantages of implementing hybrid AI on edge devices8.4 Tackling resource constraints and latency issues9 Federated learning and hybrid information systems9.1 Federated learning9.2 Hybrid information systems9.3 Related research on federated learning and hybrid information systems9.4 Federated learning in hybrid AI architectures9.5 Privacy and security considerations in federated hybrid learning10 Evaluating and benchmarking hybrid AI systems10.1 Metrics for assessing the performance of hybrid models10.2 Challenges in benchmarking and comparison of hybrid AI systemsAssignment questions
Rakhi Chauhan Hybrid approaches for improving cybersecurity and network intrusion system
1 Introduction2 Related work2.1 Comparison with existing techniques3 Challenges in improving cybersecurity and network intrusion systems4 Limitations of cybersecurity and network intrusion system5 Conclusions and future workAssignment questions
Abhijit Paul, Kunal Das, Saurav Sen IoT security enhancement through blockchain solutions
1 Introduction2 Threats to IoT data securityKey features2.1 The perception layer2.2 The network layer2.3 The application layer3 Blockchain as a solution4 Blockchain with IoT5 ConclusionAssignment questions

Jatin Arora, Saravjeet Singh, Monika Sethi, Gaganpreet Kaur, G.S. Pradeep Ghantasala Securing cloud data exchange related to IoT devices: key challenges and its machine learning solutions
1 Introduction2 Attacks on IoT infrastructure3 Security challenges3.1 Design privacy3.2 System testing3.3 Architectural privacy3.4 Minimization of data4 ML and cyberattack detection4.1 Machine learning techniques5 Machine learning challenges for IoT5.1 Resource constrained5.2 Data transmission challenges5.3 ML framework challenges6 Machine learning solutions of cloud data security7 ConclusionAssignment questions
G. Nagendra Babu, K. Harikrishna, K. Venkatewara Rao Hybrid information systems for modeling traffic management and control
1 Introduction1.1 Traffic management challenges in urban environments1.2 Limitations of traditional traffic systems1.3 Hybrid information systems: An overview1.4 Objectives of the chapter2 Data collection for hybrid information systems2.1 Sources of traffic data2.2 Data acquisition techniques and challenges2.3 Data quality and preprocessing3 Data integration and fusion for hybrid information systems3.1 Methods for integrating diverse data sources3.2 Fusion techniques to combine heterogeneous data3.3 Challenges in data integration and fusion4 Hybrid modeling techniques for traffic management and control4.1 Overview of traditional traffic modeling approaches4.2 Introduction to hybrid modeling and its advantages4.3 Integration of machine learning, optimization, and simulation5 Adaptive traffic control systems5.1 Design and architecture of adaptive traffic control systems5.2 Real-time decision-making using hybrid models6 Traffic prediction and forecasting6.1 Methods for traffic prediction7 Intelligent route guidance systems7.1 Design and functionality of intelligent route guidance systems8 Incident detection and management8.1 Incident detection technologies8.2 Incident management and response8.3 Benefits of incident detection and management8.4 Challenges and considerations9 Case studies9.1 Case study 1: real-time incident detection in smart city9.2 Case study 2: incident management in high-traffic corridor10 Future trends and challenges in incident detection and management10.1 Future trends10.2 ChallengesAssignment questions
Vishal Jain, Archan Mitra Integrative hybrid information systems for enhanced traffic maintenance and control in Bangalore: a synchronized approach
1 Introduction2 Literature review2.1 Current systems and limitations2.2 Advancements in related technologies3 Methodology3.1 An overview of the system design3.2 Sample3.3 Data collection methods3.4 Data analysis method4 The development of an assessment framework for evaluating environmental benefits4.1 Estimation of emission reduction4.2 Analysis of energy efficiency4.3 Assessment of sustainable urban mobility4.4 Monitoring environmental quality4.5 Assessment of long-term impacts5 Findings6 Discussion6.1 Analysis and interpretation of results6.2 Theoretical implications7 ConclusionAssignment questions
Rohit Rastogi, Yati Varshney A comprehensive study for weapon detection technologies for surveillance under different YoloV8 models on primary data
1 Motivation2 Scope of the study3 Introduction3.1 Advancements in weapon detection technologies and systems3.2 Challenges and solutions: ensuring effective weapon detection measures3.3 The influence of AI and machine learning on weapon detection technology3.4 Incorporating weapon detection systems into public safety infrastructures3.5 Ethical implications and privacy concerns surrounding weapon detection technologies4 Literature review5 Methodology and setup design of experiment5.1 Algorithms used5.2 Network requirements5.3 Datasets5.4 Hardware requirements5.5 Software requirements5.6 OS requirements5.7 Steps of executions5.8 Flowchart5.9 Block diagram5.10 Use case diagram6 Results and discussion6.1 Performance of Yolov8s.pt model6.2 Performance of Yolov8x.pt6.3 Discussion7 Novelties8 Recommendations9 Future research directions and limitations9.1 Limitations9.2 Future directions10 ConclusionsAssignment questions
Sateesh Kourav, Kirti Verma, Mukul Jangid, Sunil Kumar Shah Strategic design of asymmetric graphene and ReS2 field-effect transistors using nonlinear optimization and machine learning
1 Introduction2 Literature review2.1 Performance metrics and characterization3 Graphene3.1 Graphene properties3.2 Applications3.3 Graphene technology3.4 Graphene producing3.5 Advantages of graphene4 Rhenium disulfide (ReS2)4.1 What is rhenium disulfide?4.2 Structure and properties of 2D rhenium disulfide4.3 Applications of rhenium4.4 Advantages of G-ReS25 Graphene-rhenium disulfide FETs5.1 Work flow of graphene5.2 Device operation and structure5.3 Transconductance5.4 Drain-induced barrier lowering5.5 Subthreshold swing (SS)6 Visual T-CAD software6.1 Graphical user interface6.2 3D parallel device simulator6.3 Main features of TCAD7 Design profile of G-ReS2 FET7.1 Design parameter7.2 Design profile8 Simulation result8.1 Performance temperature range parameters of proposed device9 Results and discussion9.1 Parameters of the device9.2 Device specifications9.3 Temperature-dependent properties10 Conclusion and future scope
Manisha Singh, Purvee Bhardwaj, Amit Kumar Mishra, Ramakant Bhardwaj Recent advancements in perfect difference networks for image recognition: a survey and analysis
1 Introduction1.1 Key features2 Theoretical foundations of perfect difference network (PDN)2.1 Perfect difference encoding2.2 Architecture overview2.3 Attention mechanisms in PDNs2.4 Training methodologies2.5 Theoretical advantages3 Recent developments in perfect difference networks for image recognition3.1 Enhanced encoding techniques3.1.1 Attention mechanisms3.1.2 Transfer learning strategies3.1.3 Robustness and adversarial defense3.1.4 Few-shot and meta-learning3.2 Improved encoding schemes in perfect difference networks for image recognition3.3 Enhanced attention mechanisms in perfect difference networks for image recognition3.4 Transfer learning strategies in perfect difference networks for image recognition4 Comparative study of transfer learning strategies in perfect difference networks for image recognition4.1 Implementation of Transfer Learning4.2 Benchmarking PDNs against state-of-the-art architectures for image recognition4.3 Performance evaluation on diverse image datasets for perfect difference networks (PDNs)5 Case study5.1 Survey of recent progress5.2 Enhanced encoding schemes5.3 Amplified attention mechanisms5.4 Strategies for transfer learning5.5 Comparative evaluation against state-of-the-art architectures5.6 Pragmatic implications and futuristic trajectories6 Practical implications and future directions6.1 Enhanced accuracy and robustness6.1.1 Few-shot learning and limited data scenarios6.1.2 Real-world applications6.1.3 Adaptation to domain-specific tasks6.2 Future directions7 ConclusionAssignment questions
Anuj Kumar Gupta, Sukhdeep Kaur, Prabhjeet Kaur, Tanuja kumari Sharma Image to text to speech: a web-based application using optical character recognition and speech synthesis
1 Introduction1.1 Key features2 Literature review3 Proposed model4 System implementation5 Results and discussion6 Conclusion and future workAssignment questions
Rajesh Sisodia, Archan Mitra, Sayani Das Biomimicry and nature-inspired solutions for environmental sustainability
1 Introduction1.1 Background2 Literature review3 Smart phone technology and biomimicry3.1 High-quality camera lenses3.2 Longer-lasting batteries3.3 Waterproof coating3.4 Regenerating screens3.5 Sound-isolating Mic4 Mobile applications and environmental psychology5 “Hejje” mobile application: a case study6 Findings6.1 Process of HCNI paradigm7 ConclusionAssignments
Gautam Yadav, Nishant Kumar, Rohit Rastogi Intelligent analysis of flowers and knowledge generation: an empirical study for agriculture 4.0
1 Introduction2 Scope of the study3 Topic organizations4 Ethical committee and funding5 Role of authors6 Gantt chart7 Introduction7.1 Agriculture: food and flower plants in South Asia7.2 Herbal and medicinal properties of flowers7.3 Global importance of flowers: recognition in health and mental fitness7.4 Knowledge extraction through project data collection7.5 Scientific data analysis, strategy, and decision-making7.6 Applying scientific temperament in flower scent and herbs industry7.7 Global use of analysis-based strategies in floweret agriculture and their impacts7.8 Knowledge tree and knowledge dimensions for different walks of life8 Background study9 Methodology and setup of experiment9.1 Experimental setup9.2 Steps in execution9.3 Methodology9.4 Diagrams and their description10 Flowchart10.1 Use case diagram10.2 ER diagram10.3 DFD level 010.4 DFD level 110.5 DFD level 210.6 Population, sample, and dropouts10.7 Category wise flower images data11 Dependent and independent variables12 Results and findings12.1 Coding snippets and model summary12.2 Research visualizations: learning performance of models12.3 Prediction12.4 Discussions and inferences13 Novelties and recommendations13.1 Novelties13.2 Recommendations13.3 Comparison of presented manuscript with other states of the art14 Future research directions and limitations14.1 Limitations14.2 Future directions15 Conclusions15.1 Technical conclusion15.2 Recommendations15.3 Future workStudent assignment questionsAnnexureKey terms and definitions
Debosree Ghosh, Pushan Kumar Dutta, Mostafa Abotaleb Harnessing the power of hybrid models for supply chain management and optimization
1 Introduction1.1 Supply chain management problem2 Enhancing demand forecasting with hybrid models2.1 Unleashing the power of AI and ML in demand forecasting2.2 Real-time data integration for agile decision-making2.3 Adaptability to seasonal variations and unforeseen events2.4 Synergy of diverse forecasting techniques2.5 Precision in handling sparse and noisy data2.6 Incorporating external factors for holistic understanding3 Optimal resource allocation3.1 Real-time visibility and decision-making3.2 Maximizing resource utilization in manufacturing with hybrid models4 Managing supply chain risks4.1 Fostering collaboration and coordination4.2 Importance of collaboration and coordination4.3 Establishing clear communication channels4.4 Data sharing and integration4.5 Shared objectives and key performance indicators (KPIs)4.6 Collaborative planning and forecasting4.7 Vendor-managed inventory (VMI)4.8 Risk sharing and mitigation4.9 Incentives for collaboration4.10 The significance of collaboration and coordination4.11 Addressing challenges and ethical considerations4.12 Challenges in supply chain collaboration4.13 Ethical considerations in supply chain collaboration4.14 Strategies to address challenges and ethical considerations5 Challenges and future directions6 ConclusionAssignment questions
Mostafa Abotaleb, Pushan Kumar Dutta Optimizing long short-term memory networks for univariate time series forecasting: a comprehensive guide
1 Introduction2 Advantages of LSTM3 Disadvantages of LSTM4 Evaluating LSTM5 Evaluation and interpretation6 Discussion7 ConclusionAssignment questions
Mostafa Abotaleb, Pushan Kumar Dutta Optimizing bidirectional long short-term memory networks for univariate time series forecasting: a comprehensive guide
1 Introduction2 Advantages of BiLSTM3 Disadvantages of BiLSTM4 Evaluating BiLSTM5 Evaluation and interpretation6 Discussion7 ConclusionAssignment questions
Mostafa Abotaleb, Pushan Kumar Dutta Optimizing convolutional neural networks for univariate time series forecasting: a comprehensive guide
1 Introduction2 Advantages of CNNs for univariate time series forecasting3 Disadvantages of CNNs for univariate time series forecasting4 Evaluating CNNs5 Evaluation and interpretation6 Discussion7 ConclusionAssignment questions
Mostafa Abotaleb, Pushan Kumar Dutta Optimizing gated recurrent unit networks for univariate time series forecasting: a comprehensive guide
1 Introduction2 Advantages of GRU2.1 Efficient learning of long-term dependencies2.2 Adaptability to sequence length variability2.3 Capability to manage sparse information2.4 Excellence in time series forecasting2.5 Broad application spectrum3 Disadvantages of GRU3.1 Computational intensity3.2 Challenges in hyperparameter optimization3.3 Vulnerability to overfitting3.4 Preprocessing demands3.5 Opaque decision processes3.6 Reliance on ample data4 Understanding univariate time series data4.1 Definition and characteristics4.2 Importance of temporal dynamics4.3 Data preprocessing5 Designing the GRU model5.1 Choosing the architecture5.2 Regularization techniques5.3 Hyperparameter tuning5.4 Training the model5.5 Model evaluation and selection5.6 Implementation and deployment5.7 Continuous monitoring and updating6 Evaluating GRU6.1 Mean absolute error (MAE)6.2 Root mean squared error (RMSE)6.3 Mean absolute percentage error (MAPE)6.4 Mean squared error (MSE)6.5 Mean squared logarithmic error (MSLE)6.6 Symmetric mean absolute percentage error (sMAPE)6.7 Evaluation and interpretation7 Discussion8 ConclusionAssignment questions
Maad M. Mijwil, Mostafa Abotaleb, Pushan Kumar Dutta Artificial intelligence-based diagnosis and treatment of childhood bronchial allergies
1 Introduction2 Bronchial allergy is common in children3 Diagnosis of bronchial allergy in children using artificial intelligence4 Associated artificial intelligence algorithms in disease diagnosis5 ConclusionAssignment questions
Index

Content preview from Hybrid Information Systems

Index

A

access control 1
accuracy 1
activation 1, 2, 3
Activation 1
adaptive traffic control systems 1
AES 1
AI in the diagnosis 1
allergen-specific IgE antibodies 1
analysis of log 1
analyzes sentiments and opinions 1
application layer 1
architectural privacy 1
architecture of IoT 1
ARIMA 1
autoencoder based on CNN and LSTM
- autoencoder based on CNN and LSTM 1
automation of threat response 1
autoregressive integrated moving average 1

B

Bayesian network 1
bidirectional long short-term memory (BiLSTM) 1
binary classifiers 1
Biomimicry 1
biomimicry; mobile application; mimesis; environmental communication
- biomimicry; mobile application; mimesis; environmental communication 1
blockchain 1, 2
book
- word 1
BPTT 1

C

cervix 1
challenges ...

Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month,
and much more.

Read now

Unlock full access

More than 5,000 organizations count on O’Reilly

O’Reilly covers everything we've got, with content to help us build a world-class technology community, upgrade the capabilities and competencies of our teams, and improve overall team performance as well as their engagement.

Julian F.

Head of Cybersecurity

I wanted to learn C and C++, but it didn't click for me until I picked up an O'Reilly book. When I went on the O’Reilly platform, I was astonished to find all the books there, plus live events and sandboxes so you could play around with the technology.

Addison B.

Field Engineer

I’ve been on the O’Reilly platform for more than eight years. I use a couple of learning platforms, but I'm on O'Reilly more than anybody else. When you're there, you start learning. I'm never disappointed.

Amir M.

Data Platform Tech Lead

I'm always learning. So when I got on to O'Reilly, I was like a kid in a candy store. There are playlists. There are answers. There's on-demand training. It's worth its weight in gold, in terms of what it allows me to do.

Mark W.

Embedded Software Engineer

Decentralized Systems and Distributed Computing

Publisher Resources

ISBN: 9783111331188

Cloud Computing

Data Engineering

Data Science

AI & ML

Programming Languages

Software Architecture

IT/Ops

Security

Design

Business

Soft Skills

Hybrid Information Systems

by Ramakant Bhardwaj, Pushan Kumar Dutta, Pethuru Raj, Abhishek Kumar, Kavita Saini, Alfonso González Briones, Mohammed K.A. Kaabar

Index

A

B

C

Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month,
and much more.