الفهرس 
Chapter 1: IntroductionOnly 14 pages are availabe for public view
 |  | from | 107 |  |  |
| | | from | 107 | | |
Abstract
The proliferation of non-structured data sources, Examples of the types of data that exist include the Internet of Things (IoT), geospatial data, e-commerce transactions, social media content, and scientific research findings, has resulted in a large volume of data that is not suitable for traditional structured data storage methods. However, the development of sophisticated analytical techniques has enabled companies to extract valuable insights from this data with unprecedented real-time analytics for big data require both accuracy and speed refers to the ability to make informed decisions and take timely actions based on data analysis. This capability is crucial for organizations to stay ahead in today’s fast-paced business environment and make data-driven decisions that drive growth and success.
The growing concern over energy and environmental issues globally has resulted in a heightened focus on reducing energy consumption. Studies have shown that, in comparison to industries such as agriculture, services, and transportation, both residential and commercial construction sectors have a relatively high energy consumption. Utilizing artificial intelligence in the building sector holds the potential for substantial energy savings, with studies suggesting a potential reduction of 10% to 30%. An AI-powered system would be capable of detecting unusual patterns of energy usage, diagnosing the issue, and providing the best solution at the most appropriate time, leading to a more efficient and sustainable building sector.
This dissertation presents the following findings:
• A high-performance web data acquisition system, known as the ’smart collector,’ has been designed and implemented using the Java programming language. The system is characterized Due to its fast speed, accuracy, and ability to handle complex websites, setting it apart from traditional collectors. In comparison to other available collectors such as Xenu, Sitemap Generator, and Screaming Frog, our smart collector offers superior features and flexibility through its pluggable components.
• A tool has been developed to automate the detection of abnormal energy consumption through the use of artificial intelligence and big data generated by the Building Management System. This software application, called the Fault Detection Tool, optimizes resource utilization, analyzes faults and complaints, and detects abnormalities in energy consumption in real-time, leading to a more efficient and sustainable building sector.
The effectiveness of the proposed tool was evaluated through experiments, wherein the algorithm was executed twice, using different datasets. The algorithm aims to handle large amounts of data by combining machine learning operations with optimization operations in a multi-user environment. This integration reduces maintenance costs and improves the speed of the fault detector, while providing essential operations for processing unstructured information. To ensure high-quality services and fast transmission speed, several important conditions were considered, such as physical time synchronization of the system and accurate data processing. Every second, vast amount of data is being transferred and stored across the globe, making them vulnerable to malicious attacks aimed at stealing or destroying the data. As a result, it is imperative to focus on developing secure techniques for data storage and transfer. Over the years, various technologies have emerged to protect data, utilizing cryptography and information hiding methods. Currently, DNA-based cryptography is gaining popularity as a secure method. The convergence of machine learning, Big Data, and DNA coding has revolutionized the field of security services, offering the possibility of unbreakable algorithms. This study explores the implementation of DNA coding characteristics, service models, and security concerns. A novel approach to secure data storage or transfer is proposed, which is both cost-effective and secure, utilizing bio-computational techniques. The tool employs a combination of machine learning, Big Data, and DNA steganography techniques, along with binary coding rules, to provide an additional layer of bio-security that is more robust than traditional cryptographic methods. Furthermore, hash function techniques are integrated to enhance the efficiency of the tool for message authentication and non-repudiation purposes.
In conclusion, the proposed technique is expected to provide a new level of security for data storage and transfer, making it more resilient against malicious attacks and ensuring the confidentiality, integrity, and availability of sensitive information.
This dissertation explores the integration of big data, machine learning, and DNA coding in order to enhance the security and efficiency of data storage and transfer. The author proposes a fast and accurate data acquisition system for the web, as well as a tool for detecting abnormal energy consumption using AI and big data. The results of the experiments are discussed, and the author highlights the use of DNA-based cryptography as a growing trend in data security. The proposed algorithm integrates machine learning, big data, and DNA steganography techniques with binary coding rules to enhance the security of data storage and transfer, surpassing the security offered by traditional cryptographic methods. The tool also incorporates hash function techniques to improve its efficiency for message authentication and non-repudiation.