Data Streams Research Articles

Fast-Vid2Vid++: Spatial-Temporal Distillation for Real-Time Video-to-Video Synthesis.

Video-to-Video synthesis (Vid2Vid) gains remarkable performance in generating a photo-realistic video from a sequence of semantic maps, such as segmentation, sketch and pose. However, this pipeline is heavily limited to high computational cost and long inference latency, mainly attributed to two essential factors: 1) network architecture parameters, 2) sequential data stream. Recently, the parameters of image-based generative models have been significantly reduced via more efficient network architectures. Existing methods mainly focus on slimming network architectures but ignore the size of the sequential data stream. Moreover, due to the lack of temporal coherence, image-based compression is not sufficient for the compression of the video task. In this paper, we present a spatial-temporal hybrid distillation compression framework, Fast-Vid2Vid++, which focuses on knowledge distillation of the teacher network and the data stream of generative models on both space and time. Fast-Vid2Vid++ makes the first attempt at time dimension to transfer hierarchical features and time coherence knowledge to reduce computational resources and accelerate inference. Specifically, we compress the data stream spatially and reduce the temporal redundancy. We distill the knowledge of the hierarchical features and the final response from the teacher network to the student network in high-resolution and full-time domains. We transfer the long-term dependencies of the features and video frames to the student model. After the proposed spatial-temporal hybrid knowledge distillation (Spatial-Temporal-HKD), our model can synthesize high-resolution key-frames using the low-resolution data stream. Finally, Fast-Vid2Vid++ interpolates intermediate frames by motion compensation with slight latency and generates full-length sequences with motion-aware inference (MAI). On standard benchmarks, Fast-Vid2Vid++ achieves a real-time performance of 30-59 FPS and saves 28-35× computational cost on a single V100 GPU.

An Ensemble-Based Semi-Supervised Learning Approach for Non-Stationary Imbalanced Data Streams with Label Scarcity

Addressing the challenges of learning from multi-class imbalanced data streams, particularly in scenarios with scarce labeled data and concept drift, remains an open problem in the field of data stream mining. Despite the prevalence of such data scenarios in real-world applications, existing approaches have yet to provide effective solutions. In this paper, we propose a novel chunk-based semi-supervised framework, GMCSSEL, which leverages an ensemble of base classifiers trained on micro-cluster centers with labels inferred through a graph-fusion and label propagation process. Our approach incorporates chunk-based incremental label propagation by integrating both current and previously inferred label information into the propagation equation, with regularization parameters applied to control their influence. Furthermore, our method includes a novel concept drift detection mechanism specifically designed for imbalanced data with label scarcity. The imbalanced data problem is addressed through a combination of graph fusion, label matrix normalization, and SMOTE techniques. Experimental results on synthetic data streams with varying class ratios and concept drifts, as well as real multi-class streams, demonstrate the superior classification performance of our approach compared to the IOE semi-supervised algorithm. Our method achieves an average increase in evaluation metrics of 12.5% across multiple data streams, with improvements ranging from 8% to 18% in G-mean, AUC, Kappa, and F1-score metrics. Statistical analysis confirms that these improvements are significant, highlighting the robustness of our approach in handling non-stationary imbalanced data streams with label scarcity.

Aqua-stream: an IoT based smart water management system for sustainable living

<p class="03IJISAEAbstract">Aqua-stream, an innovative internet of things (IoT) enabled water management system, utilizes the power of long short-term memory (LSTM) networks, a sophisticated time-series forecasting machine learning technique with Kafka. Aqua-stream seamlessly integrates LSTM within the Kafka streaming architecture for efficient real-time data processing, ensuring quick responses to emerging water management needs. LSTM is employed for real-time anomaly detection, dynamically analyzing streaming data to prevent leaks through automated shut-off valves. The system’s comprehensive dashboard utilizes LSTM insights for live water quality analysis; adaptive scheduling based on individual preferences and personalized recommendations, enhancing cost-effective water management. This streamlined approach extends to the smart gardening system, where LSTM guides automation for optimal plant care incorporating sensors to monitor soil moisture, temperature, and sunlight levels. This system automatically adjusts watering and lighting to ensure optimal conditions for plant growth. Users can control and monitor their garden remotely via a smartphone, facilitating plant care while saving water and energy. Aqua-stream redefines home water management, offering a holistic solution that combines intelligent water conservation with smart gardening for a sustainable and connected living experience. Aqua-stream represents a seamless integration of LSTM-based machine learning and IoT technologies, offering an intelligent, yet simplified, solution for sustainable and connected living.</p>

NeuDen: a framework for the integration of neuromorphic evolving spiking neural networks with dynamic evolving neuro-fuzzy systems for predictive and explainable modelling of streaming data

NeuDen: a framework for the integration of neuromorphic evolving spiking neural networks with dynamic evolving neuro-fuzzy systems for predictive and explainable modelling of streaming data

Subsampling Algorithms for Irregularly Spaced Autoregressive Models

With the exponential growth of data across diverse fields, applying conventional statistical methods directly to large-scale datasets has become computationally infeasible. To overcome this challenge, subsampling algorithms are widely used to perform statistical analyses on smaller, more manageable subsets of the data. The effectiveness of these methods depends on their ability to identify and select data points that improve the estimation efficiency according to some optimality criteria. While much of the existing research has focused on subsampling techniques for independent data, there is considerable potential for developing methods tailored to dependent data, particularly in time-dependent contexts. In this study, we extend subsampling techniques to irregularly spaced time series data which are modeled by irregularly spaced autoregressive models. We present frameworks for various subsampling approaches, including optimal subsampling under A-optimality, information-based optimal subdata selection, and sequential thinning on streaming data. These methods use A-optimality or D-optimality criteria to assess the usefulness of each data point and prioritize the inclusion of the most informative ones. We then assess the performance of these subsampling methods using numerical simulations, providing insights into their suitability and effectiveness for handling irregularly spaced long time series. Numerical results show that our algorithms have promising performance. Their estimation efficiency can be ten times as high as that of the uniform sampling estimator. They also significantly reduce the computational time and can be up to forty times faster than the full-data estimator.

A Space-Efficient One-Pass Online SVM Algorithm

In this paper we consider the problem of training a Support Vector Machine (SVM) online using a stream of data in random order. We provide a fast online training algorithm for general SVM on very large datasets. Based on the geometric interpretation of SVM known as the polytope distance, our algorithm uses a gradient descent procedure to solve the problem. With high probability our algorithm outputs an [Formula: see text]-approximation result in constant time and space, which is independent of the size of the dataset, where [Formula: see text]-approximation means that the separating margin of the classifier is almost optimal (with error [Formula: see text]), and the number of misclassified training points is very small (with error [Formula: see text]). Experimental results show that our algorithm outperforms most of existing online algorithms, especially in the space requirement aspect, while maintaining high accuracy.

Learning to Detect Novel Species with SAM in the Wild

AbstractThis paper tackles the limitation of a closed-world object detection model that was trained on one species. The expectation for this model is that it will not generalize well to recognize the instances of new species if they were present in the incoming data stream. We propose a novel object detection framework for this open-world setting that is suitable for applications that monitor wildlife, ocean life, livestock, plant phenotype and crops that typically feature one species in the image. Our method leverages labeled samples from one species in combination with a novelty detection method and Segment Anything Model, a vision foundation model, to (1) identify the presence of new species in unlabeled images, (2) localize their instances, and (3) retrain the initial model with the localized novel class instances. The resulting integrated system assimilates and learns from unlabeled samples of the new classes while not “forgetting” the original species the model was trained on. We demonstrate our findings on two different domains, (1) wildlife detection and (2) plant detection. Our method achieves an AP of 56.2 (for 4 novel species) to 61.6 (for 1 novel species) for wildlife domain, without relying on any ground truth data in the background.

Machine Learning in Health Anylitics and Patient Monitoring Solomon Kavuta and Mr Joel Mulepa Dmi St John The Baptist University, Lilongwe, Malawi

The integration of machine learning techniques in healthcare has revolutionized the way predictive analytics and patient monitoring are conducted. This transformation is reshaping traditional healthcare practices by harnessing the power of advanced computational methods to analyze vast amounts of patient data. Machine learning algorithms, which excel at detecting patterns and making predictions, leverage this data to forecast disease onset, progression, and treatment outcomes. This capability enables healthcare providers to adopt proactive measures, facilitating early intervention and the development of personalized treatment plans tailored to individual patients' needs. The potential of machine learning in healthcare is vast and multifaceted. By continuously analyzing real-time patient data streams from various sources such as electronic health records (EHRs), medical imaging, genomic information, and data from wearable devices, these algorithms can identify subtle changes in a patient's condition that may indicate the early stages of a disease or the risk of an adverse event. This continuous monitoring allows for timely interventions that can prevent complications, reduce the severity of diseases, and improve overall patient outcomes. For example, machine learning can help predict the likelihood of a patient developing conditions like diabetes or heart disease, allowing for lifestyle changes and medical interventions that can mitigate these risks before they become severe health issues. Moreover, machine learning facilitates remote patient monitoring, which has become increasingly important in the context of modern healthcare. With the advent of wearable devices and Internet of Things (IoT) sensors, it is now possible to collect and analyze health data outside of traditional clinical settings. These technologies enable healthcare providers to monitor patients in real-time, regardless of their location, ensuring continuous care and oversight. This is particularly beneficial for managing chronic diseases, where regular monitoring can significantly improve patient management and outcomes. For instance, remote monitoring of patients with heart conditions can detect early signs of arrhythmias or other issues, prompting immediate medical responses that can prevent more serious complications. The transformative impact of machine learning on healthcare delivery extends beyond patient monitoring and predictive analytics. It also includes enhancing diagnostic accuracy, optimizing treatment protocols, and streamlining administrative processes. By reducing the need for frequent hospital visits and enabling more efficient use of healthcare resources, machine learning can help lower healthcare costs while improving the quality of care provided to patients. Additionally, the ability to analyze large datasets quickly and accurately can aid in medical research, uncovering new insights into disease mechanisms and potential treatments.

Snowy Dove: An open-sourcetoolkit for pre- processing of Chinese Gaofen series data.

Since the launch of the Chinese High-resolution Earth Observation System (CHEOS) program, China has strengthened its research and development in the field of satellite remote sensing. A large number of sensors has been or will be launched, providing very large data streams which all require processing of the engineering data, as provided by the instruments, to physical data which will be used for further processing and interpretation. To handle such large data streams we developed a one-click batch pre-processing toolkit for CHEOS remote sensing data as described in this paper. In this toolkit, IDL language and environment are used as the primary program combined with other programming languages developed in this research. In this paper, we first describe the Gaofen (GF) series data used in this research and then introduce the function design and realization of this one-click batch pre-processing toolkit. Some examples will be presented to illustrate the application of the toolkit to data from several CHEOS satellites.

Toward Cross-Lingual Social Event Detection with Hybrid Knowledge Distillation

Recently published graph neural networks (GNNs) show promising performance at social event detection tasks. However, most studies are oriented toward monolingual data in languages with abundant training samples. This has left the common lesser-spoken languages relatively unexplored. Thus, in this work, we present a GNN-based framework that integrates cross-lingual word embeddings into the process of graph knowledge distillation for detecting events in low-resource language data streams. To achieve this, a novel cross-lingual knowledge distillation framework, called CLKD, exploits prior knowledge learned from similar threads in English to make up for the paucity of annotated data. Specifically, to extract sufficient useful knowledge, we propose a hybrid distillation method that consists of both feature-wise and relation-wise information. To transfer both kinds of knowledge in an effective way, we add a cross-lingual module in the feature-wise distillation to eliminate the language gap and selectively choose beneficial relations in the relation-wise distillation to avoid distraction caused by teachers’ misjudgments. Our proposed CLKD framework also adopts different configurations to suit both offline and online situations. Experiments on real-world datasets show that the framework is highly effective at detection in languages where training samples are scarce.

Infectious Disease Modeling

Infectious diseases pose a persistent challenge to public health worldwide. Recent global health crises, such as the COVID-19 pandemic and Ebola outbreaks, have underscored the vital role of infectious disease modeling in guiding public health policy and response. Infectious disease modeling is a critical tool for society, informing risk mitigation measures, prompting timely interventions, and aiding preparedness for healthcare delivery systems. This article synthesizes the current landscape of infectious disease modeling, emphasizing the integration of statistical methods in understanding and predicting the spread of infectious diseases. We begin by examining the historical context and the foundational models that have shaped the field, such as the SIR (susceptible, infectious, recovered) and SEIR (susceptible, exposed, infectious, recovered) models. Subsequently, we delve into the methodological innovations that have arisen, including stochastic modeling, network-based approaches, and the use of big data analytics. We also explore the integration of machine learning techniques in enhancing model accuracy and responsiveness. The review identifies the challenges of parameter estimation, model validation, and the incorporation of real-time data streams. Moreover, we discuss the ethical implications of modeling, such as privacy concerns and the communication of risk. The article concludes by discussing future directions for research, highlighting the need for data integration and interdisciplinary collaboration for advancing infectious disease modeling.

PYRAMID CHANNEL-BASED FEATURE ATTENTION NETWORK WITH ENSEMBLE LEARNING-BASED UAV IMAGE CLASSIFICATION ON IoT-ASSISTED REMOTE SENSING ENVIRONMENT

Advances in Unmanned Aerial Vehicles (UAVs), otherwise recognized as drones, have tremendous promise in improving the wide-ranging applications of the Internet of Things (IoT). UAV image classification using deep learning (DL) is an amalgamation to modernize data analysis, collection, and decision-making in a variety of sectors. IoT devices collect information in real time, while remote sensing captures data afar without direct contact. UAVs equipped with sensors offer high-quality images for classification tasks. DL techniques, especially the convolutional neural networks (CNNs), analyze data streams, extracting complicated features for the accurate classification of objects or environmental features. This synergy enables applications including urban planning and precision agriculture, fostering smarter disaster response, decision support systems, and efficient resource management. This paper introduces a novel Pyramid Channel-based Feature Attention Network with an Ensemble Learning-based UAV Image Classification (PCFAN-ELUAVIC) technique in an assisted remote sensing environment. The PCFAN-ELUAVIC technique begins with the contrast enhancement of the UAV images using the CLAHE technique. Following that, the feature vectors are derived by the use of the PCFAN model. Meanwhile, the hyperparameter tuning procedure is executed by the inclusion of a vortex search algorithm (VSA). For image classification, the PCFAN-ELUAVIC technique comprises an ensemble of three classifiers like long short-term memory (LSTM), graph convolutional networks (GCNs), and Hermite neural network (HNN). To exhibit the improved detection results of the PCFAN-ELUAVIC system, an extensive range of experiments are carried out. The experimental values confirmed the enhanced performance of the PCFAN-ELUAVIC model when compared to other techniques.

The Postdigital Panorama

University teachers are in the midst of a messy and entangled postdigital era. They face a constant stream of data and increasingly visible teaching as a consequence of digital media and AI spaces. This prompts the need for identity work to reconsider the personal, professional and societal meanings of the role of teachers in a world where people and machines are becoming further interwoven. Narrowing it down to social media spaces that encompass context collapse, it is becoming increasingly difficult to draw a line between personal and professional facets of life. Higher education teachers, who contribute to social media, construct fluid, greatly changeable and intermingled identities. The current study aims to conceptualise the practices and roles that may guide these emerging identities using a theoretical vignette as a tool. The presented case can initiate the discussions on who we are and who we are becoming in the current realities and prompt questions about learning and teaching in the networked society.

Empowering Urdu sentiment analysis: an attention-based stacked CNN-Bi-LSTM DNN with multilingual BERT

Sentiment analysis (SA) as a research field has gained popularity among the researcher throughout the globe over the past 10 years. Deep neural networks (DNN) and word vector models are employed nowadays and perform well in sentiment analysis. Among the different deep neural networks utilized for SA globally, Bi-directional long short-term memory (Bi-LSTM), BERT, and CNN models have received much attention. Even though these models can process a wide range of text types, Because DNNs treat different features the same, using these models in the feature learning phase of a DNN model leads to the creation of a feature space with very high dimensionality. We suggest an attention-based, stacked, two-layer CNN-Bi-LSTM DNN to overcome these glitches. After local feature extraction, by applying stacked two-layer Bi-LSTM, our proposed model extracted coming and outgoing sequences by seeing sequential data streams in backward and forward directions. The output of the stacked two-layer Bi-LSTM is supplied to the attention layer to assign various words with varying values. A second Bi-LSTM layer is constructed atop the initial layer in the suggested network to increase performance. Various experiments have been conducted to evaluate the effectiveness of our proposed model on two Urdu sentiment analysis datasets named as UCSA-21 and UCSA, and an accuracies of 83.12% and 78.91% achieved, respectively.

LLMasMMKG: LLM Assisted Synthetic Multi-Modal Knowledge Graph Creation For Smart City Cognitive Digital Twins

The concept of a Smart City (SC) Cognitive Digital Twin (CDT) presents significant potential for optimizing urban environments through sophisticated simulations, predictions, and informed decision-making. Comprehensive Knowledge Representations (KRs) that effectively integrate the diverse data streams generated by a city are crucial to realizing this potential. This paper addresses this by introducing a novel approach that leverages Large Language Models (LLMs) to automate the construction of synthetic Multi-Modal (MM) Knowledge Graphs (KGs) specifically designed for a SC CDT. Recognizing the challenges in fusing and aligning information from disparate sources, our method harnesses the power of LLMs for natural language understanding, entity recognition, and relationship extraction to seamlessly integrate data from sensor networks, social media feeds, official reports, and other relevant sources. Furthermore, we explore the use of LLM-driven synthetic data generation to address data sparsity issues, leading to more comprehensive and robust KGs. Initial outputs demonstrate the effectiveness of our approach in constructing semantically rich and interconnected synthetic KGs, highlighting the significant potential of LLMs for advancing SC CDT technology.

Event-Driven Data Pipelines : A Cloud-Based Approach to Real-Time Data Processing

This article comprehensively analyzes event-driven data pipelines in cloud computing environments, examining their architecture, implementation considerations, and real-world applications. The article explores the fundamental components of event-driven systems, from event sources and message brokers to processing layers, while evaluating their performance characteristics and reliability mechanisms. Through detailed analysis of system architectures, we investigate the integration of various cloud services and their role in enabling scalable, real-time data processing. The article demonstrates how modern event-driven architectures achieve sub-millisecond processing times and handle millions of events per second while maintaining system resilience. Our findings reveal significant improvements in operational efficiency across various industries, including financial services, marketing automation, and IoT monitoring solutions. The article also addresses critical implementation aspects, including security frameworks, integration protocols, and best practices for system optimization. These insights provide valuable guidance for organizations leveraging event-driven architectures in their digital transformation initiatives. The article concludes that event-driven data pipelines represent a crucial advancement in data processing technology, offering unprecedented capabilities in handling real-time data streams while maintaining scalability, reliability, and cost-effectiveness.

Revisiting streaming anomaly detection: benchmark and evaluation

Anomaly detection in streaming data is an important task for many real-world applications, such as network security, fraud detection, and system monitoring. However, streaming data often exhibit concept drift, which means that the data distribution changes over time. This poses a significant challenge for many anomaly detection algorithms, as they need to adapt to the evolving data to maintain high detection accuracy. Existing streaming anomaly detection algorithms lack a unified evaluation framework that validly assesses their performance and robustness under different types of concept drifts and anomalies. In this paper, we conduct a systematic technical review of the state-of-the-art methods for anomaly detection in streaming data. We propose a new data generator, called SCAR (Streaming data generator with Customizable Anomalies and concept dRifts), that can synthesize streaming data based on synthetic and real-world datasets from different domains. Furthermore, we adapt four static anomaly detection models to the streaming setting using a generic reconstruction strategy as baselines, and then compare them systematically with 9 existing streaming anomaly detection algorithms on 76 synthesized datasets that have various types of anomalies and concept drifts. The challenges and future research directions for anomaly detection in streaming data are also presented.

Challenges in Mathematics Arising from Theoretical and Computational Chemistry

The combination of theoretical chemistry and mathematics represents a significant advancement in science since it has yielded insights into the enigmas surrounding atoms and molecules. The advancement of technology has greatly benefited drug development, leading to significant advancements in both medicine and materials research. This summary discusses innovative methodologies and computational challenges in the expansive domain of theoretical and computational chemistry. Despite the computational challenges associated with the Schrodinger equation and Density Functional Theory (DFT), quantum mechanics offers a basic understanding of the behaviour of molecules and atoms. While MD simulations may not handle long-range interactions and complex configuration spaces, they nonetheless excel at capturing various time scales of molecular behaviour. Nevertheless, the process of transforming abstract notions into computer models for the purpose of solving MD simulations continues to be difficult; statistical mechanics offers a theoretical framework for understanding MD simulations. Data-driven methodologies and machine learning have significantly transformed the perspective of computational chemistry by enabling the observation and comprehension of very complex chemical interactions. We must also address concerns about interpretability, reliability in limited data streams, and system transferability. These challenges expedite the advancement of novel materials, product designs, and pharmaceuticals by leveraging machine learning and integrating it with specialised domain expertise. We used available data from many reputable databases, spanning the time period from 2010 to 2024. It is imperative to prioritise the advancement of multiscale modelling techniques and hybrid quantum-classical tools in order to achieve sufficient mastery over chemical phenomena. Another potential benefit is the use of novel mathematical models to uncover previously unknown patterns and connections in genetic data. The most effective way to tackle mathematical problems is by employing a straightforward approach and engaging in collaboration with experts from other fields. By adopting this approach, we can effectively address significant societal issues and propel advancements in chemistry. Keywords: mathematics, computational, chemistry, theoretical, challenges, quantum mechanics

Transferring knowledge by budget online learning for multiobjective multitasking optimization

Multiobjective multitasking optimization (MO-MTO) has attracted increasing attention in the evolutionary computation field. Evolutionary multitasking (EMT) algorithms can improve the overall performance of multiple multiobjective optimization tasks through transferring knowledge among tasks. Negative transfer resulting from the indeterminacy of the transferred knowledge may bring about the degradation of the algorithm performance. Identifying the valuable knowledge to transfer by learning the historical samples is a feasible way to reduce negative transfer. Taking this into account, this paper proposes a budget online learning based EMT algorithm for MO-MTO problems. Specifically, by regarding the historical transferred solutions as samples, a classifier would be trained to identified the valuable knowledge. The solutions which are considered containing valuable knowledge will have more opportunity to be transfer. For the samples arrive in the form of streaming data, the classifier would be updated in a budget online learning way during the evolution process to address the concept drift problem. Furthermore, the exceptional case that the classifier fails to identify the valuable knowledge is considered. Experimental results on two MO-MTO test suits show that the proposed algorithm achieves highly competitive performance compared with several traditional and state-of-the-art EMT methods.

Soft Prompt-tuning with Self-Resource Verbalizer for short text streams

Short text streams such as real-time news and search snippets have attained vast amounts of attention and research in recent decades, the characteristics of high generation velocity, feature sparsity, and high ambiguity accentuate both the importance and challenges to language models. However, most of the existing short text stream classification methods can neither automatically select relevant knowledge components for arbitrary samples, nor expand knowledge internally instead of rely on external open knowledge base to address the inherent limitations of short text stream. In this paper, we propose a Soft Prompt-tuning with Self-Resource Verbalizer (SPSV for short) for short text stream classification, the soft prompt with self-resource knowledgeable expansion is conducted for updating label words space to address evolved semantic topics in the data streams. Specifically, the automatic constructed prompt is first generated to instruct the model prediction, which is optimized to address the problem of high velocity and topic drift in short text streams. Then, in each chunk, the projection between category names and label words space, i.e. verbalizer, is updated, which is constructed by internal knowledge expansion from the short text itself. Through comprehensive experiments on four well-known benchmark datasets, we validate the superb performance of our method compared to other short text stream classification and fine-tuning PLMs methods, which achieves up to more than 90% classification accuracy with the counts of data chunk increased.