Using AI for Real-Time Big Data Processing and Analysis with Integration of Multi-Agent Systems

Recent advances in mobile technologies have enabled a plethora of new applications. The hardware capabilities of mobile devices, however, are still insufficient for real-time stream data processing (e.g., real-time video stream). In order to process real-time streaming data, most existing applications offload the data and computation to a remote cloud service, such as Apache Storm or Apache Spark Streaming. Offloading streaming data, however, has high costs for users, e.g., significant service fees and battery consumption. To address these challenges, we design, implement and evaluate Mobile Storm, the first stream processing platform for mobile clouds, leveraging clusters of local mobile devices to process real-time stream data. In Mobile Storm, we model the workflow of a real-time stream processing job and decompose it into several tasks so that the job can be executed concurrently and in a distributed manner on multiple mobile devices. Mobile Storm was implemented on Android phones and evaluated extensively through a real-time HD video processing application. The result shows that Mobile Storm effectively processes HD Video Stream in a mobile cloud, which would be impossible on a single mobile device.

Chapter 18 - Big Astronomical Datasets and Discovery of New Celestial Bodies in the Solar System in Automated Mode by the CoLiTec Software

The rapid growth of data streams, propelled by the proliferation of sensors and Internet of Things (IoT) devices, presents significant challenges for real-time clustering of high-dimensional data. Traditional clustering algorithms struggle with high dimensionality, memory and time constraints, and adapting to dynamically evolving data. Existing dimensionality reduction methods often neglect feature ranking, leading to suboptimal clustering performance. To address these issues, we introduce E-Stream, a novel entropy-based clustering algorithm for high-dimensional data streams. E-Stream performs real-time feature ranking based on entropy within a sliding time window to identify the most informative features, which are then utilized with the DenStream algorithm for efficient clustering. We evaluated E-Stream using the NSL-KDD dataset, comparing it against DenStream, CluStream, and MR-Stream. The evaluation metrics included the average F-Measure, Jaccard Index, Fowlkes-Mallows Index, Purity, and Rand Index. The results show that E-Stream outperformed the baseline algorithms in both clustering accuracy and computational efficiency while effectively reducing dimensionality. E-Stream also demonstrated significantly less memory consumption and fewer computational requirements, highlighting its suitability for real-time processing of high-dimensional data streams. Despite its strengths, E-Stream requires manual parameter adjustment and assumes a consistent number of active features, which may limit its adaptability to diverse datasets. Future work will focus on developing a fully autonomous, parameter-free version of the algorithm, incorporating mechanisms to handle missing features and improving the management of evolving clusters to enhance robustness and adaptability in dynamic IoT environments.

Due to their real time nature, microblog streams are a rich source of dynamic information, for example, about emerging events . Existing techniques for discovering such events from a microblog stream in real time (such as Twitter trending topics), have several lacunae when used for discovering emerging events; extant graph based event detection techniques are not practical in microblog settings due to their complexity; and conventional techniques, which have been developed for blogs, web-pages, etc., involving the use of keyword search, are only useful for finding information about known events. Hence, in this paper, we present techniques to discover events that are unraveling in microblog message streams in real time so that such events can be reported as soon as they occur. We model the problem as discovering dense clusters in highly dynamic graphs. Despite many recent advances in graph analysis, ours is the first technique to identify dense clusters in massive and highly dynamic graphs in real time. Given the characteristics of microblog streams, in order to find clusters without missing any events, we propose and exploit a novel graph property which we call short-cycle property . Our algorithms find these clusters efficiently in spite of rapid changes to the microblog streams. Further we present a novel ranking function to identify the important events. Besides proving the correctness of our algorithms we show their practical utility by evaluating them using real world microblog data. These demonstrate our technique's ability to discover, with high precision and recall, emerging events in high intensity data streams in real time. Many recent web applications create data which can be represented as massive dynamic graphs. Our technique can be easily extended to discover, in real time, interesting patterns in such graphs.

Chapter 32 - StatStream: Statistical Monitoring of Thousands of Data Streams in Real Time

In such areas as transport, healthcare, business process management, financial services, complex event processing (CEP) systems are becoming in demand. Large volumes of streams of events are generated and collected by these systems. Real-time processing of event stream data is essential. Based on current and past events, a decision is made, and forecasting future events is an alternative goal. For the fastest reaction to non-standard behavior, it is necessary to process data streams in real time, it means, as quickly as possible. That's why it is important to find new technologies which can speed up data processing. In this article expensive queries in CEP is identified, effective optimizations to improve their performance significantly is proposed. It is developed and implemented algorithm, which should decrease processing time. The results are compared with state-of-the-art CEP system.

The ability to interpret spatiotemporal data streams in real-time is critical for a range of systems. However, processing vast amounts of spatiotemporal data out of several sources, such as online traffic, social platforms, sensor networks, and other sources, is a considerable challenge. The major goal of this study is to create a framework for processing and analyzing spatiotemporal data from multiple sources with irregular shapes so that researchers can focus on data analysis instead of worrying about the data sources' structure. We introduced a novel spatiotemporal data paradigm for true-real-time stream processing, which enables high-speed and low-latency real-time data processing, with these considerations in mind. A comparison of two state-of-the-art real-time process architectures was offered, as well as a full review of the various open-source technologies for real-time data stream processing, and their system topologies were also presented. Hence, this study proposed a brand-new framework that integrates Apache Kafka for spatiotemporal data ingestion, Apache flink for true real-time processing of spatiotemporal stream data, as well as machine learning for real-time predictions, and Apache Cassandra at the storage layer for distributed storage in real-time. The proposed framework was compared with others from the literature using the following features: Scalability (Sc), prediction tools (PT), data analytics (DA), multiple event types (MET), data storage (DS), Real-time (Rt), and performance evaluation (PE) stream processing (SP), and our proposed framework provided the ability to handle all of this task.

This paper explores the transformative potential of real-time data streaming and artificial intelligence (AI) in the context of e-commerce live streaming shopping. By leveraging advance technologies such as Storm, Trident, Samza, and Spark Streaming, businesses can process and analyze data in real-time, enhancing consumer engagement and driving sales in real time. This paper reviews the literature on live streaming selling, product promotion, and multichannel sales, and discusses the challenges and opportunities associated with these technologies. The findings provide valuable insights for businesses and researchers aiming to harness the power of real-time data streaming in the dynamic landscape of social commerce using real time streaming

Multiple unmanned aerial vehicle (multi-UAV) systems have gained significant attention in applications, such as aerial surveillance and search and rescue missions. With the recent development of state-of-the-art multiagent reinforcement learning (MARL) algorithms, it is possible to train multi-UAV systems in collaborative and competitive environments. However, the inherent vulnerabilities of multiagent systems pose significant privacy and security risks when deploying general and conventional MARL algorithms. The presence of even a single Byzantine adversary within the system can severely degrade the learning performance of UAV agents. This work proposes a Byzantine-resilient MARL algorithm that leverages a combination of geometric median consensus and a robust state update model to mitigate, or even eliminate, the influence of Byzantine attacks. To validate its effectiveness and feasibility, the authors include a multi-UAV threat model, provide a guarantee of robustness, and investigate key attack parameters for multiple UAV navigation scenarios. Results from the experiments show that the average rewards during a Byzantine attack increased by up to 60% for the cooperative navigation scenario compared with conventional MARL techniques. The learning rewards generated by the baseline algorithms could not converge during training under these attacks, while the proposed method effectively converged to an optimal solution, proving its viability and correctness.

This paper presents a novel data-driven method for modeling combined sewer overflows (CSOs) in real-time. This method treats CSO event generation as a threshold process that is triggered by increasingly intense rainfall events, and predicts the likelihood of a CSO given input conditions using a Bayesian network. The fusion of relevant data from multiple agencies into a unified data stream in real time is described, and a hierarchical modeling strategy is proposed that will facilitate the exploration of the causes of CSOs and direct research into the adaptive management of combined sewer systems using the Chicago wastewater system as a case study.

Traditional multi-agent reinforcement learning (MARL) algorithms typically implement global parameter sharing across various types of heterogeneous agents without meticulously differentiating between different action semantics. This approach results in the action semantic conflict problem, which decreases the generalization ability of policy networks across heterogeneous types of agents and decreases the cooperation among agents in intricate scenarios. Conversely, completely independent agent parameters significantly escalate computational costs and training complexity. To address these challenges, we introduce an adaptive MARL algorithm named Generalized Action-Prediction Optimization (GAPO). First, we introduce the Generalized Action Space (GAS), which represents the union of all agent actions with distinct semantics. All agents first compute their unified representation in the GAS, and then generate their heterogeneous action policies with different available action masks. Second, in order to further improve cooperation between heterogeneous groups, we propose a Cross-Group Prediction (CGP) loss, which adaptively predicts the action policies of other groups by leveraging trajectory information. We integrate the GAPO into both value-based and policy-based MARL algorithms, giving rise to two practical algorithms: G-QMIX and G-MAPPO. Experimental results obtained within the SMAC, MPE, MAMuJoCo, and RPE environments demonstrate the superiority of G-QMIX and G-MAPPO over several state-of-the-art MARL methods, validating the effectiveness of our proposed adaptive generalized MARL approach.

Streaming data is widely generated in our lives. This has promoted a lot of research on streaming data mining, such as streaming data clustering and filtering. In our work, we present a problem about data stream processing, namely, streaming data sorting. There are some important characteristics of streaming data. Firstly, streaming data comes in the form of streams. It is usually assumed that streaming data is infinite, so it cannot be stored completely in memory. Secondly, we must process the streaming data in real time, otherwise we may lose the opportunity to deal with it forever. Based on these characteristics, we propose a dynamic algorithm that can make full use of memory and minimize error to solve the problem of streaming data sorting, which is further combined with the BFR algorithm to sort a particular type of streaming data. Some experiments are conducted to confirm the effectiveness of the proposed algorithms.

Processing a data stream in real time is a crucial issue for several applications, however processing a large amount of data from different sources, such as sensor networks, web traffic, social media, video streams and other sources, represents a huge challenge. The main problem is that the big data system is based on Hadoop technology, especially MapReduce for processing. This latter is a high scalability and fault tolerant framework. It also processes a large amount of data in batches and provides perception blast insight of older data, but it can only process a limited set of data. MapReduce is not appropriate for real time stream processing, and is very important to process data the moment they arrive at a fast response and a good decision making. Ergo the need for a new architecture that allows real-time data processing with high speed along with low latency. The major aim of the paper at hand is to give a clear survey of the different open sources technologies that exist for real-time data stream processing including their system architectures. We shall also provide a brand new architecture which is mainly based on previous comparisons of real-time processing powered with machine learning and storm technology.

© 2019 Association for Computing Machinery.Number of connected devices is steadily increasing and these devices continuously generate data streams. These data streams are often high dimensional and contain concept drift. Real-time processing of data streams is arousing interest despite many challenges. Clustering is a method that does not need labeled instances (it is unsupervised) and it can be applied with less prior information about the data. These properties make clustering one of the most suitable methods for real-time data stream processing. Moreover, data embedding is a process that may simplify clustering and makes visualization of high dimensional data possible. There exist several data stream clustering algorithms in the literature, however no data stream embedding method exists. UMAP is a data embedding algorithm that is suitable to be applied on data streams, but it cannot adopt concept drift. In this study, we have developed a new method to apply UMAP on data streams, adopt concept drift and cluster embedded data instances using any distance based clustering algorithms.

Evolution of the Internet of Things (IoT) makes a revolution in connecting, monitoring, controlling, and managing things, objects, and almost surroundings through the Internet. To reveal the potential of IoT, rich knowledge has to be extracted, indexed, and shared securely in real time. Recent comprehensive researches on IoT spot the light on main correlative challenges, such as security, scalability, heterogeneity, and big data. Due to the heterogeneity of IoT applications that produce a large volume of a variety of data streams in real time, mining, securing, and analyzing IoT data become tedious and challenging tasks. Indexing sensory data is one of data mining techniques, which ease information retrieval. But ordinary indexing methods are not fit with such massive and dynamic data; where indexes become out-of-date once they are built. Clustering, data reduction, and summarization present promising solutions for enabling low-power security and balanced indexing. This article presents a novel method for dynamic data reduction and summarization using dynamic time warping (DTW), which also presents a balanced architecture for enabling balanced indexing based on similarity data fusion. Data reduction-based prediction models enable real-time search and secure discovery for Smart Things (SThs). The results of the proposed model were proved using real examples and data sets. Using the Szeged-weather data set similar SThs data is reduced by 95%. Thus, indexes sizes could be reduced, and using smart scheduling, crawling cycle length could be expanded.