Skip to main content
Fachgebiete
Automobil + Motoren Bauwesen + Immobilien Business IT + Informatik Elektrotechnik + Elektronik Energie + Nachhaltigkeit Finance + Banking Management + Führung Marketing + Vertrieb Maschinenbau + Werkstoffe Versicherung + Risiko
DE
EN
Themenseiten
Organisationspsychologie Projektmanagement Marketing Smart Manufacturing
Bücher
Zeitschriften
Weitere Formate
Podcasts Webinare Technik Webinare Wirtschaft Kongresse Veranstaltungskalender Awards
Jetzt Einzelzugang starten
Zugang für Unternehmen
Referenzkunden
MTZ-Fachkongress

Antriebe und Energiesysteme von morgen


Austausch von Automobil- und Energiewirtschaft

Am 14./15. Mai geht es in Chemnitz um die Mobilitätswende durch Elektro- und Wasserstofffahrzeuge.
Erweiterte Suche
Anmelden
nach oben

2024 | Buch

Introduction to Spatiotemporal Data Kapitel lesen Erstes Kapitel lesen

Spatiotemporal Data Analytics and Modeling

Techniques and Applications

herausgegeben von: John A, Satheesh Abimannan, El-Sayed M. El-Alfy, Yue-Shan Chang

Verlag: Springer Nature Singapore

Buchreihe : Big Data Management

Enthalten in: Springer Professional "Wirtschaft+Technik" , Springer Professional "Technik" , Springer Professional "Wirtschaft"

Einloggen, um Zugang zu erhalten
insite
SUCHEN

Über dieses Buch

With the growing advances in technology and transformation to digital services, the world is becoming more connected and more complex. Huge heterogeneous data are generated at rapid speed from various types of sensors. Augmented with artificial intelligence and machine learning and internet of things, latent relations, and new insights can be captured helping in optimizing plans and resource utilization, improving infrastructure, and enhancing quality of services.

A “spatial data management system” is a way to take care of data that has something to do with space. This could include data such as maps, satellite images, and GPS data. A temporal data management system is a system designed to manage data that has a temporal component. This could include data such as weather data, financial data, and social media data. Some advanced techniques used in spatial and temporal data management systems include geospatial indexing for efficient querying and retrieval of location-based data, time-series analysis for understanding and predicting temporal patterns in datasets like weather or financial trends, machine learning algorithms for uncovering hidden patterns and correlations in large and complex datasets, and integration with Internet of Things (IoT) technologies for real-time data collection and analysis. These techniques, augmented with artificial intelligence, enable the extraction of latent relations and insights, thereby optimizing plans, improving infrastructure, and enhancing the quality of services.

This book provides essential technical knowledge, best practices, and case studies on the state-of-the-art techniques of artificial intelligence and machine learning for spatiotemporal data analysis and modeling. The book is composed of several chapters written by experts in their fields and focusing on several applications including recommendation systems, big data analytics, supply chains and e-commerce, energy consumption and demand forecasting,and traffic and environmental monitoring. It can be used as academic reference at graduate level or by professionals in science and engineering related fields such as data science and engineering, big data analytics and mining, artificial intelligence, machine learning and deep learning, cloud computing, and internet of things.

Inhaltsverzeichnis

Frontmatter

Spatiotemporal Data Management Techniques

Frontmatter
Chapter 1. Introduction to Spatiotemporal Data
Abstract
Spatial and temporal data are generated for analytics and surveillance actions in fields like road transportation, satellite-related applications, moving action detection, etc. Various sensing technologies and social media applications have utilised spatial and temporal data. In this chapter, the study has been conducted to detail spatial and temporal data views. Later the spatial and temporal data categories were analysed alongside their merits and needfulness. Further, various spatial and temporal data models have been analysed from different aspects of the applications related to moving objects as dynamic regions and dynamic objects detection and observation. Spatial and temporal data representation techniques have been studied and compared to the highlights for further research. Furthermore, spatial and temporal data-handling methods have been studied to enrich the applications of moving objects over day-to-day societal activities alongside merits and demerits. Finally, spatial and temporal data applications have been reviewed and listed with their merits and demerits.
N. M. Balamurugan, K. Maithili, N. Revathi, R. Gayathri, M. Adimoolam
Chapter 2. Recommendation System Using Spatial-Temporal Network for Vehicle Demand Prediction
Abstract
Intelligent transportation and smart vehicle management research will be revolutionized by the introduction of spatiotemporal approaches. These approaches enable the analysis of object movement in time and space, prediction of traffic flow, optimization of transport routes, and understanding of driver and passenger behavior. The potential applications of spatiotemporal research extend to developing transportation-related games, IoT applications, and improving safety, pollution reduction, and vehicle demand. By leveraging spatiotemporal research, transportation professionals can gain a deeper understanding of complex transportation systems, device strategies for enhanced efficiency, emissions reduction, and accurate vehicle demand prediction. Additionally, spatiotemporal research can identify areas for improving public transportation and serve as a foundation for developing future systems. Its promise lies in boosting transportation efficiency, reducing environmental impact, and improving safety. Understanding human behavior and decision-making through spatiotemporal analysis offers insights for tailored infrastructure and services, addressing diverse needs like those of children, elderly, and disabled populations. Combining spatiotemporal data with demographic information aids in comprehending transportation equity issues, identifying service gaps, and driving improvement. Achieving sustainable transportation systems that cater to all members of society hinges on addressing these equity concerns. Ultimately, the utilization of spatiotemporal research for vehicle demand prediction has the power to transform the field, fostering efficient, equitable, and sustainable transportation systems.
Kishore Anthuvan Sahayaraj, G. Balamurugan
Chapter 3. Spatial-Based Big Data and Large-Scale Network Management
Abstract
Handling of location (spatial)- and time (temporal)-based data is enormous since they are represented as images, videos, and audio. There must be challenging to store those data in today’s trends, and storage will be hectic in the future since generation and storage are large in volume. In this chapter, it is essential to study large data concerning spatial and temporal data and their networks. Initially, the study initiated the evolution of big and large-scale networks. Later various management techniques were analyzed on big data and large-scale networks concerning spatial.
Furthermore, they essentially studied temporal-based big data and extensive scale network management. Finally, various applications of big data and large-scale networks have been studied, and analytics represented their impact and challenges concerning spatial and temporal data. The phrase “big data” commonly has various ideas, from gathering data from outside sources and storing and preserving it to using analytical methods and tools to analyze the data. It is a popular term in both academics and business. The intent of this section of the book is to give a summary of current big data analytics. Principles to highlight the significance of big data analytics for decision-making applications. To protect data availability, confidentiality, and integrity, it takes various modules to implement security measures for big data. Here are some standard modules used in big data security implementations: In our digital world, security breaches advanced by malicious software (malware) attacks keep growing and pose a significant security risk. Recent malware identification process uses dynamic and static analysis of behavior patterns, and malware signatures, take a lot of time, and could be more successful in identifying real-time unknown malware.
The detailed phase can be eliminated using sophisticated machine-learning techniques built in Python. The solution to the current project’s issue focuses on machine learning and big data analytics. Malware poses a severe risk to a user’s computer system by stealing sensitive data or impeding security. The growth of the smartphone industry has provided malware creators with new opportunities. There is a need to counteract stealth malware strategies since malware varieties are expanding at an astronomical rate every year. This chapter dataset is imported the initial portion of the CSV file in numerical form and sections of the malware image are imported and loaded for better understanding. The machine learning techniques are applied to the dataset in the second portion. The ultimate goal is to provide a novel image-processing method that uses artificial learning techniques and deep learning architectures to achieve a rate of actual accuracy. Our proposed model will outperform conventional machine learning algorithms, according to a comparative analysis of our model. Overall, this work lays the path for the most accurate and efficient malware detection ever.
R. Sheeja, S. Vanaja, Adimoolam M, Chidambaranathan Bibin
Chapter 4. Handling Uncertainty in Spatiotemporal Data
Abstract
Spatial technologies forge massive datasets fast and constantly. This gigantic dataset consists of the time series forecasting or spatial interpolation issue to time and space dimensions. Spatiotemporal data can be further modeled with different statistical, physical, and artificial intelligence (AI) methods, but due to handling uncertainty in spatiotemporal data is the major challenge in front of these models. The chapter’s fundamental motivation is to analyze the challenges and strategies for virtually managing uncertainty in spatiotemporal data. The primary difficulties behind the data are high-level feature extractions and long-term memory modeling. These data are technically intensive and result in inadequate model configuration and parameterization. Most AI models oriented with these data need more interpretability and essentially require elaborate training but can model complex nonlinear and Non-Gaussian problems. Predictive uncertainty comes from data and models, which a probability distribution and Bayesian inference could estimate. Therefore, this chapter addresses the detailed strategies for handling uncertainty, including algorithms and approaches for data management. The structure of uncertain data management requires exploring the components of uncertainty management, including data structures and relevant algorithms. This chapter also concentrates on the distinct challenges of handling uncertainty in moving object data and provides strategies for addressing these challenges. Another motivation behind this chapter is to study different domains where spatiotemporal data is encountered on an enormous scale and provides a close look at the computational and I/O requirements of several analysis algorithms for such data. Handling uncertainty in spatiotemporal data is a hot topic in the research area. This chapter will provide the researchers extensive and revised literature review and future research direction, which will undoubtedly be valuable for addressing the challenges in addressing uncertainty in spatiotemporal data in diverse applications. The view inside the chapter provides state-of-the-art advances in spatiotemporal data handling and highlights new generation necessities to solve uncertainty in spatiotemporal data.
Shivaji D. Pawar, Varsha S. Pawar, Satheesh Abimannan
Chapter 5. Multimodal Spatial-Temporal Prediction and Classification Using Deep Learning
Abstract
“Spatial-temporal” (ST) data is time series data from multiple locations. Data is unpredictable, making predictions difficult. For a variety of urban tasks, such as estimating the speed of traffic and the demand for taxis, an accurate prediction that is based on this kind of data is required. Because of this assumption, the methods that are currently being used that are based on deep learning can only produce one possible outcome. As a consequence of this, they are unable to comprehend how the future will comprise a wide variety of components and how these components will interact with one another. Also, the current method operates under the presumption that information that is spatial and that which is temporal are essentially distinct, and as a result, each must be investigated separately. The chapter introduces a novel approach that utilises spatial-temporal convolutional neural networks in conjunction with Bi-LSTM and enhanced generative adversarial networks (E-GAN) to effectively capture non-linear correlations present in the data distribution. This is achieved through the use of inverse mapping from the forecast distribution. The spatio-temporal correlation network is a modelling technique that captures the distribution of pixels in both space and time. This approach enables the random sampling of latent variables to generate multiple future scenarios. This is accomplished by modelling the spatial distribution of pixels. This sampling can be carried out for a very wide variety of different possible outcomes (STCN). It is a stochastic adversarial network that learns to perform variational inference on data and generate data together with other people through implicit distribution modelling. Education is the means by which one can accomplish both of these goals. E-GAN also allows the combination of external factors, which further improves model learning, and it does this without any additional work. E-GAN outperforms the baseline models and significantly improves performance, as shown by extensive testing on two datasets derived from the real world.
K. Suresh Kumar, K. Abirami, C. Helen Sulochana, T. Ananth Kumar, Sunday A. Ajagbe, C. Morris
Chapter 6. Spatiotemporal Object Detection and Activity Recognition
Abstract
Spatiotemporal object detection and activity recognition are essential components in the advancement of computer vision, with broad applications spanning surveillance, autonomous driving, and smart stores. This chapter offers a comprehensive overview of the techniques and applications associated with these concepts. Beginning with an introduction to the fundamental principles of object detection and activity recognition, we discuss the challenges and limitations posed by existing methods. The chapter progresses to explore spatiotemporal object detection and activity recognition, which entails capturing spatial and temporal information of moving objects in video data. A hierarchical model for spatiotemporal object detection and activity recognition is proposed, designed to maintain spatial and temporal connectivity across frames. Additionally, the chapter outlines various metrics for evaluating the performance of object detection and activity recognition models, ensuring their accuracy and effectiveness in real-world applications. Finally, we underscore the significance of spatiotemporal object detection and activity recognition in diverse fields such as surveillance, autonomous driving, and smart stores, emphasizing the potential for further research and development in these areas. In summary, this chapter provides a thorough examination of spatiotemporal object detection and activity recognition, from the foundational concepts to the latest techniques and applications. By presenting a hierarchical model and performance evaluation metrics, the chapter serves as a valuable resource for researchers and practitioners seeking to harness the power of computer vision in a variety of domains.
Vimal Kumar, Shobhit Jain, David Lillis

Applications of Spatiotemporal Data Analytics

Frontmatter
Chapter 7. Spatio-temporal Data Analytics for e-Waste Management System Using Hybrid Deep Belief Networks
Abstract
In the most recent few decades, there has been a significant increase all over the world in the amount of waste electronic equipment. This is a result of a number of factors, including an increase in production, management rules that are ineffective, recycling practices that are inefficient, and safety risks that are unacceptable. Because of the harmful emissions that are released into the air, water, and soil when electronic waste is disposed of in landfills, this practice has the potential to be detrimental to both human health and the environment. The process of recycling used electronic equipment results in the production of several distinct categories of secondary waste, including solids, liquids, and gases. When waste, such as electronic waste, is thrown away in an improper manner, it has a detrimental effect not only on human health but also on the environment. In this work, we propose a hybrid deep learning model (HDLM) which comprises Fuzzy-based Spatio-Temporal Optimization Mechanism (FSTOM) in addition to Deep Belief networks (DBN) for e-waste prediction. During network training and error checking, residual learning is designed to prevent oscillations. In this chapter, we propose using a novel algorithm called MSOK (modified self-organizing map and K-Means algorithm) to create a profile for each type of waste produced. To take advantage of the best features of both statistical modelling and deep belief network modelling, these hybrid models combine the two. The findings suggest that cutting-edge data analysis techniques could be employed to obtain more accurate statistics regarding garbage generation. Compared with the existing models, the proposed model performs well effectively in determination and classification of the e-wastes with proper optimization strategies.
K. Suresh Kumar, C. Helen Sulochana, D. Jessintha, T. Ananth Kumar, Mehdi Gheisari, Christo Ananth
Chapter 8. Spatiotemporal and Intelligent Transportation Forecasting
Abstract
Spatiotemporal-based intelligent transportation systems are increasingly being integrated into various surveillance systems. To enhance the efficiency of these systems, automated forecasting was introduced to identify and penalize non-compliant behaviors. This chapter explores a range of location-based transportation forecasting systems and the necessary adaptations for smart cities. Additionally, the frameworks of transportation systems using intelligent methods have been evaluated to analyze their merits and demerits. Subsequently, route-based prediction was examined for its real-time application efficacy. Building upon spatial forecasting methods, their essential techniques and adaptation potentials have been explored for the transportation application of spatiotemporal data. In conclusion, analysis and forecasting-based performance metrics are presented, focusing on intelligent transportation systems across various countries, along with their challenges. As a key focus, the applications of spatiotemporal-based intelligent transportation forecasting are discussed in detail.
K. Maithili, S. Leelavathy, G. Karthi, M. Adimoolam
Chapter 9. Spatio-Temporal Supply Chains and E-Commerce
Abstract
Supply Chain Management (SCM) has emerged as a pivotal element of contemporary business strategies, deftly incorporating advancements in Machine Learning (ML) and Deep Learning (DL) to bolster market performance. In the E-commerce sector, SCM, enhanced by ML, is driving critical transformative changes, which have become particularly vital in the post-pandemic landscape. This evolution in SCM is setting new benchmarks in process efficiency, encompassing comprehensive risk mitigation and substantial reduction in operational costs. It ensures swift delivery and elevated customer satisfaction, while also offering deep insights into the automation of goods delivery within E-commerce. This is a crucial aspect in sculpting a globally competitive SCM model. By utilizing advanced ML software, supply chain managers in E-commerce can refine their portfolios and identify the most fitting suppliers, thus propelling their businesses towards greater efficiency and effectiveness. This article is dedicated to exploring these significant developments. It begins by examining the principles of spatial and temporal data analysis. On this foundation, it elaborates on the implementation of SCM through a variety of modern techniques, with a special emphasis on ML and DL applications. These techniques are instrumental in formulating a framework grounded in spatial-temporal data analysis. Conclusively, the article delineates the design and practical details of SCM, integrating diverse characteristics and the latest technological innovations.
S. Vijayalakshmi, Sathya Shanmugasundaram, P. Padmanabhan, S. Jerald Nirmal Kumar
Chapter 10. Spatiotemporal Renewable Energy Techniques and Applications
Abstract
This chapter provides an overview of the field of spatiotemporal data analysis in the context of renewable energy applications. With the increasing use of renewable energy resources, more advanced and accurate analysis of spatiotemporal data is needed to optimize energy systems. The chapter discusses the importance, limitations, and applications of spatiotemporal data analytics, including predicting solar and wind energy production, analyzing the impact of weather events on renewable energy systems, and optimizing the placement and performance of renewable energy systems. One of the biggest challenges, however, is the volume and complexity of the data, which includes weather patterns, energy production, and use. Spatiotemporal data analytics for renewable energy applications is rapidly growing, but little is known about its potential benefits and limitations. More research is needed to fully understand how this technology can improve the reliability, efficiency, and sustainability of renewable energy systems. The chapter provides readers with a comprehensive view of the methodologies, algorithms, datasets, techniques, and frameworks used by various researchers in their state-of-the-art work on the applications of spatiotemporal data analytics in renewable energy systems. This chapter also discusses future research directions to improve the availability of renewable energy systems worldwide.
Abhishek Vyas, Satheesh Abimannan, Po-Ching Lin, Ren-Hung Hwang
Chapter 11. Environmental Spatiotemporal Data Analytics
Abstract
Environmental spatiotemporal data analytics (ESTDA) is a field that combines environmental science, data science, and geographic information systems to explore the relationship between environmental phenomena and their spatial and temporal variability. ESTDA has been used to address a wide range of environmental issues, such as climate change, pollution, biodiversity loss, and natural disasters. The goal of this field is to identify patterns, trends, and anomalies in environmental data that can help scientists and policymakers make informed decisions. ESTDA relies on a variety of analytical techniques, including statistical models, machine learning algorithms, remote sensing, and spatial analysis. These techniques allow researchers to extract meaningful information from large and complex datasets, including environmental monitoring networks, satellite imagery, and citizen science data. By analysing these data, ESTDA can provide insights into the drivers of environmental change, the impacts of human activities on the environment, and the effectiveness of environmental policies and management strategies. Overall, ESTDA has the potential to improve our understanding of environmental systems and inform more effective environmental decision-making. However, it also faces a number of challenges, such as data quality and availability, computational limitations, and need for interdisciplinary collaboration. Addressing these challenges will be crucial for the continued advancement of ESTDA and its potential to contribute to sustainable development and conservation efforts. The chapter aims at addressing the overall concept of ESTDA, its issues, and challenges.
Shubhangi Tidake, Bandana Mahapatra, Suchit Subodh Mishra
Chapter 12. Future and Research Perspectives of Spatiotemporal Data Management Methods
Abstract
This chapter presents different spatiotemporal data management models, challenges and future direction of spatiotemporal research. The spatiotemporal data model and analysis consists of four main parts such as indexing, query processing, updations and applications. The indexing and data management uses to manage past, present and future (PPF) data. The data management method is generally used to manage PPF methods and also used to manage spatial-based priority management. This chapter presents PPF data, spatial-based priority-based methods and corresponding limitations and suggestions. Finally, different issues and limitations of spatiotemporal methods in general-based, task-based, application-based and implementation-based spatiotemporal data management and future research direction are presented.
T. F. Michael Raj, G. Vallathan, Eswaran Perumal, P. Sudhakar, John A.
Metadaten
Titel
Spatiotemporal Data Analytics and Modeling
herausgegeben von
John A
Satheesh Abimannan
El-Sayed M. El-Alfy
Yue-Shan Chang
Copyright-Jahr
2024
Verlag
Springer Nature Singapore
Electronic ISBN
978-981-9996-51-3
Print ISBN
978-981-9996-50-6
DOI
https://doi.org/10.1007/978-981-99-9651-3

Premium Partner

    Bildnachweise