Real-time Data Research Articles

Development of an Online Power Distribution Information Management System

This research focuses on designing and implementing an Online Power Distribution Information Management System (PIMS) to address the growing complexity and demands of modern power grids. Traditional manual approaches to power distribution often lead to inefficient operations, delayed fault detection, and poor data management. By integrating real-time monitoring, data analytics, and secure online platforms, the proposed system significantly enhances reliability, reduces downtime, and improves overall operational efficiency. Employing the Structured Systems Analysis and Design Methodology (SSADM), the study systematically gathered requirements, modeled system functionalities, and developed a robust architecture comprising a user-friendly interface, scalable database management, and strong security protocols. Key components include an analytics engine for load forecasting and fault prediction, as well as seamless integration with existing systems such as SCADA. Evaluation metrics demonstrate the system’s effectiveness in swiftly identifying network anomalies—achieving a 97% fault detection accuracy—and reducing outage durations by 30% compared to older solutions. Advanced analytics achieved predictive accuracies above 95%, thereby optimizing resource allocation and informing proactive maintenance. Real-time data capture and storage enable operators to promptly respond to changing conditions, while stringent security measures and encryption protocols bolster cyber-resilience. The Online Power Distribution Information Management System paves the way for a more sustainable, efficient, and secure power distribution framework, positioning utilities to better handle emerging challenges such as renewable energy integration and growing consumer demands.

Acquisition of Biomedical Data Using IoT

In this paper, we present a comprehensive Internet of Things (IoT)-based health monitoring system that measures key vital signs, including heart rate (BPM), oxygen saturation (SpO2), temperature, and electrocardiogram (ECG) signals, using an ESP32 microcontroller. The system leverages a variety of sensors, such as the MAX30105 for optical measurement of heart rate and SpO2, a dedicated Pulse Sensor for additional BPM detection, a DHT11 for temperature readings, and an ECG module connected to an analog input. Data is transmitted over a Wi-Fi network to the Thing Speak platform, allowing for real-time remote monitoring, data visualization, and analysis. To efficiently handle multiple sensor readings and data uploads without blocking, we utilize Free RTOS task scheduling on the ESP32. Our experimental results demonstrate the system’s reliability, ease of use, and accuracy in capturing vital health parameters, illustrating its potential in telemedicine, remote patient.

IOT-ENHANCED CANCER TREATMENT: A STUDY OF HEREDITARY RISK, LIFESTYLE FACTORS, AND REAL-TIME MONITORING TECHNOLOGIES

Shaping the universe of the Internet of Things (IoT) means rewriting how cancer treatment is given to patients. Research approach followed in this study is based on the comprehensive examination of IoT in carrying out cancer interventions through its part of real-time data collection and processing. Genetic predisposition determines cancer. Nevertheless, it is primarily unscrupulous management of such determinants in preventive care. IoT wearables and health monitoring wearables take pictures and allow continuous tracking of high-risk patients for cancer so that any deviation can activate proper preventive measures. Based on what is now understood, healthcare professionals stop the route of mere treatment of disease and rearrange their models into more and more predictive ones. Along the way, with the development of these devices, it becomes possible for the genetic mutation and the biomarker to be monitored in real-time. Lifestyle risk factors are mostly linked with cancer growth and development, including diet, activity, and exposure to carcinogens. IoT devices with wearable sensors and mobile health apps can define to patients exactly how active they are and the behaviours they are in their environment. For instance, air pollution sensors can detect an amount of pollutants that are linked to lung cancer, and fitness trackers can incentivize behavior as safety procedures. Such a change raises consumer engagement, which fosters the development of improved practices and reduction in risk factors. The unique characteristic of IoT in oncology, direct monitoring, provides real-time and constant feedback of various physiological states of the patients. Smart implants and biosensors are among the networked devices that generate real-time information about tumors, efficacy of treatment, and side effects. With this constantly growing amount of data, strategic planning is enhanced so that the treatment programs can be modified more effectively and accurately. Real-time monitoring enables deviation from the conventional cancer treatment to more sophisticated medicine, under strict monitoring and observation of any genetic hazards and lifestyle habits. The approach results in improved clinical outcomes and allows patients to take an active role in the self-management of their health. With the development of such IoT technologies, there is unlimited potential for revolutionizing the prevention and treatment of cancer, ultimately paving the way for the future of personalized, preventive, and patient-centered oncology.

A Predictive Models for Advertisement Campaign Budget Allocation

This study explores the role of predictive models in optimizing advertisement campaign budget allocation. As digital marketing grows more complex, predictive models offer data-driven insights that help advertisers allocate budgets more efficiently. These models use machine learning to analyze past performance, predict trends, and optimize resource distribution across channels, improving campaign outcomes and return on investment (ROI). Techniques such as real-time bidding (RTB), customer segmentation, and multi-touch attribution have enhanced budget allocation. However, challenges like data quality, model interpretability, and integration complexity limit widespread use. Predictive models are integrated into platforms like Google Ads and Facebook Ads Manager, optimizing cost-per-click (CPC) and conversion rates. Balancing automation with human oversight remains crucial. Research should focus on real-time data integration and ethical concerns around data privacy to ensure responsible use. Refining these models will empower advertisers to make better data-driven decisions, improving budget allocation and campaign success.

Development of an IoT-Enabled Smart Electricity Meter for Real-Time Energy Monitoring and Efficiency

Smart meters play an important role in energy management systems as they provide essential parameters for real-time monitoring, protection, and control that enable informed decisions for the end-users and the utility grid. However, available systems are high-cost solutions with different hardware and software, which provide limited measuring parameters with certain accuracy. This work aims to develop and implement an innovative smart electricity meter (SEM) system that surpasses conventional designs by incorporating advanced features like noninvasive sensors, manual signal calibration, and flexible communication modes. The developed SEM supports real-time data transmission via IoT and provides superior accuracy in measuring harmonics and frequency, addressing key challenges in energy monitoring. This work contributes to real-time energy monitoring and energy management systems in residential and industrial applications.

AR Furniture App: Challenges and Future Prospects

Augmented Reality (AR) applications are revolutionizing user experiences by seamlessly blending digital content with the real world. This paper presents an AR app designed to enhance interaction, visualization, and engagement in various domains, including education, entertainment, retail, and healthcare. The app leverages advanced AR technologies such as real-time object recognition, spatial mapping, and interactive 3D overlays to create immersive experiences. Using a smartphone or AR headset, users can interact with virtual elements overlaid on their physical surroundings. The app incorporates intuitive controls, AI-powered personalization, and cloud integration for real-time data processing. This AR solution aims to improve user engagement, accessibility, and efficiency across industries, demonstrating the potential of AR in shaping the future of digital interaction.

Intelligent Control on Industrial Vinyl Chloride Monomer Column: A System Identification and Artificial Intelligence Based Control Approach

In the production of vinyl chloride monomer (VCM), the separation of VCM vapors from ethylene dichloride (EDC) in the distillation column is complicated due to uncertain dynamic behavior and nonlinearity of the process and results in poor controlling of the column which may overlook product quality. In this regard, the column is simulated with integrated tuned-controllers using Aspen Plus dynamics. For system identification of the VCM column, the nonlinear autoregressive model with exogenous inputs (NLARX) gives a higher Fit% for the real-time data in comparison with the first order plus time delay (FOPTD) model. The study shows the application of artificial neural network (ANN) and adaptive neuro-fuzzy inference system (ANFIS) based control strategies, alongside a traditional proportional-integral-derivative (PID) controller for the control of the top composition and bottom composition of the VCM column. The results indicate that for top composition, the ANFIS-based controller having an integral time absolute error (ITAE) value of 0.132 outperforms ANN-based controller with an ITAE value of 0.78 in terms of set point tracking, and a similar behavior is found for bottom composition. In terms of disturbance rejection, the ANFIS having an ITAE value of 0.036 outperforms ANN having an ITAE value of 1.03 for top composition and shows the same behavior for bottom composition while the PID control exhibits significantly lower performance in both set point tracking and disturbance rejection.

Research Opportunities in Human Life Applications based on Artificial Intelligence, Machine Learning and Internet of Things using Graph Theory

This is review based paper which consist of different research opportunities in human life applications based on AI, ML & IoT using graph theory and also listed different software tools can help for same. The integration of Artificial Intelligence (AI), Machine Learning (ML) and the Internet of Things (IoT) has revolutionized various fields, offering promising solutions to human life applications. Graph theory, with its ability to model complex networks and relationships, plays a crucial role in optimizing and enhancing the functionality of AI, ML and IoT systems. This paper explores emerging research opportunities in leveraging graph theory to address challenges in human life applications, focusing on areas such as healthcare, smart cities, transportation and environmental monitoring. In healthcare, graph-based models can optimize personalized treatment plans and improve patient monitoring by analyzing the interconnectedness of variables such as medical histories and real-time data from IoT-enabled devices. In smart cities, IoT devices generate vast amounts of data and graph theory can be used to model traffic, energy consumption and social interactions to create more efficient urban environments. Furthermore, in transportation, AI and ML algorithms can leverage graph structures to improve route planning, traffic management and fleet optimization. The synergy of AI, ML, IoT, and graph theory offers new frontiers for research in these areas, with the potential to significantly improve the quality of human life. This paper emphasizes the need for interdisciplinary research to fully realize the potential of these technologies in real-world applications.

Real-Time Data Integrity Validation Using Blockchain for Autonomous Vehicles

This article presents a comprehensive framework for implementing blockchain-based data integrity validation in autonomous vehicles. The proposed system addresses critical challenges in securing real-time sensor data through a hybrid architecture combining Hyperledger Fabric with Apache Kafka. By integrating distributed ledger technology with optimized data processing mechanisms, the system achieves both security and performance requirements essential for autonomous vehicle operations. The architecture incorporates smart contracts for data validation, multi-layered security protocols, and efficient data streaming capabilities. Results demonstrate that the proposed solution successfully balances the competing demands of data security and real-time processing, making it suitable for deployment in production autonomous vehicle environments.

Enhancing pharmaceutical supply chains: unveiling the power of digital control tower through stress testing

ABSTRACT Pharmaceutical supply chain disruptions can hinder patient access to essential treatments. This research uses a system dynamics model to explore strategies for enhancing supply chain resilience. We focus on the role of a ‘digital control tower', an advanced management system that improves visibility through real-time monitoring, data analysis, and better communication. Our findings suggest that digital control towers enable pharmaceutical supply chains to better handle disruptions, with real-time monitoring and rapid responses facilitating swift adjustments and optimised operations. This study highlights the importance of digital control towers in improving the stability and flexibility of pharmaceutical supply chains, reducing delays, and ensuring timely medication delivery.

Research on Intelligent Local Energy System and Power Metering Based on Supply-side Demand Based on KNN

Based on the K-Nearest Neighbor algorithm, this paper deeply studies the intelligent local energy system and power metering problems of supply-side demand. Through the analysis of a large amount of energy consumption and supply data, we have built an intelligent system that can accurately predict and meet local energy demand. Specifically, we collected electricity consumption data for the past five years, including multi-dimensional information such as daily consumption, seasonal changes, and weather factors. Through the KNN algorithm, we successfully identified the key factors affecting electricity consumption and established a prediction model. The model can predict the power demand in the future based on historical data and real-time information, providing strong decision support for the supply side. In practical application, the system also plays an important role in power metering. Through the monitoring and analysis of real-time power data, the system can accurately calculate the power consumption of each region, providing data support for energy management and optimization. In the application of our pilot city, we’ve achieved remarkable results. The precision of our power demand prediction system has exceeded 90%, while the margin of error in power measurements remains below 2%. These improvements have had a profound impact on energy utilization efficiency and economic performance. Moreover, through meticulous data analysis, we’ve discovered that optimizing the energy mix and increasing the share of renewable energy are highly effective strategies for cutting energy costs and mitigating environmental pollution. Looking ahead, we intend to delve deeper into how the KNN algorithm and other cutting-edge technologies can be harnessed to further enhance the sustainability of our local energy system. The research in this paper not only provides theoretical support for the development of intelligent local energy system, but also provides a new idea for the innovation of power metering technology.

Privacy and security of smart irrigation data using IOTA distributed ledger

ABSTRACT IoT-enabled smart agriculture enhances farming with real-time data insights but faces security and scalability challenges. This study integrates IOTA’s distributed ledger technology into smart irrigation systems, leveraging its Tangle architecture for fee-less, lightweight, and scalable transactions. The system ensures tamper-proof data integrity and real-time decision-making, crucial for precision agriculture. Experimental results show efficient data transmission (336 bytes) with processing times of 0.7–1.3 seconds and rapid data retrieval (1×10⁻⁶– 4×10⁻⁶ seconds). A comparative analysis highlights IOTA’s superiority over traditional blockchain systems, demonstrating its robustness, scalability, and efficiency for secure, real-time IoT-based smart farming.

Power Transmission Line Fault Detection and Classification

It is very important to find short circuit faults of power transmission lines (PTL) quickly and efficiently. Most methods in the literature use classification algorithms for fault detection, but their use in real-time applications increases fault detection time. The reason for this that while the fault detection process is performed with the classification algorithm, the features of incoming data must be extracted continuously by using a window function. In this study, principal component analysis (PCA) or independent component analysis (ICA) algorithms that are suitable for real-time fault detection are proposed to decrease the fault detection time. Besides, time-domain statistical properties of the PTL signals computed over a period of time are proposed to increase classification speed and accuracy. The results show that PCA and ICA algorithms can detect all faults in real-time data streams, and the classification results are 100% for 10 faults with the proposed features.

Leveraging Cloud Computing for Real-Time Marketing Analytics: A Technical Perspective

This article examines how cloud computing has revolutionized marketing analytics by enabling real-time data processing and decision-making capabilities previously unattainable with traditional on-premise systems. It presents a comprehensive technical analysis of cloud-native architectures for marketing analytics, detailing the multi-layered framework that spans from data ingestion through to action delivery. The article explores how organizations have overcome the historical limitations of traditional analytics environments—including data silos, batch processing constraints, and limited computational resources—through the implementation of cloud-based platforms. The technical architecture is dissected across its primary components: the data ingestion layer that captures customer interactions as they occur; the processing layer that transforms raw data into actionable insights within milliseconds; specialized storage technologies optimized for analytical workloads; the analytics layer with its visualization and machine learning capabilities; and the action layer that enables immediate customer engagement. The article further addresses critical implementation considerations related to performance optimization, scalability, data governance, and cost management. Through examination of real-world applications like dynamic audience segmentation, predictive customer lifetime value modeling, and personalized content orchestration, it demonstrates how cloud technologies deliver substantial competitive advantages. The article concludes by exploring emerging trends at the intersection of artificial intelligence and cloud computing that will shape the next generation of marketing analytics capabilities.

Pitfalls and Strategies for Implementing and Sustaining an Otolaryngology Perioperative Registry in Mekelle, Ethiopia.

Surgical registries have been widely adopted in high-income countries to improve patient outcomes. However, similar data-driven initiatives are still scarce in low- and middle-income countries (LMICs). This study aimed to address the challenges of implementing a perioperative registry for otolaryngology-head and neck surgery (OHNS) in Mekelle, Ethiopia, and to assess strategies for ensuring its long-term sustainability. The registry was developed using REDCap, through a collaborative effort between otolaryngologists in the United States and Ethiopia, ensuring its relevance to the local context. On-site training sessions were conducted for 13 OHNS residents and four senior surgeons to facilitate their use of the registry. A Wi-Fi router was installed in the operating room to enable real-time data entry. Continuous support was provided through remote communication between the local team and the U.S. research team. Sustainability strategies focused on fostering local ownership, integrating the registry into existing workflows, and maintaining continuous data monitoring. Despite facing challenges like intermittent internet connectivity and issues with workflow integration, the local team successfully integrated the registry into routine clinical and surgical practices. Key strategies included providing dedicated Wi-Fi routers, modifying registry fields for improved efficiency, and emphasizing the registry's value to the institution. Ongoing collaboration between the local team and the U.S. team enabled continuous optimization and data collection. The successful implementation of this perioperative registry underscores the importance of engaging local stakeholders and integrating sustainable workflows. This initiative serves as a model for other LMICs seeking to establish surgical registries that enhance data-driven decision-making at both the patient and institutional levels.

Environmental sound recognition on embedded devices using deep learning: a review

Sound recognition has a wide range of applications beyond speech and music, including environmental monitoring, sound source classification, mechanical fault diagnosis, audio fingerprinting, and event detection. These applications often require real-time data processing, making them well-suited for embedded systems. However, embedded devices face significant challenges due to limited computational power, memory, and low power consumption. Despite these constraints, achieving high performance in environmental sound recognition typically requires complex algorithms. Deep Learning models have demonstrated high accuracy on existing datasets, making them a popular choice for such tasks. However, these models are resource-intensive, posing challenges for real-time edge applications. This paper presents a comprehensive review of integrating Deep Learning models into embedded systems, examining their state-of-the-art applications, key components, and steps involved. It also explores strategies to optimise performance in resource-constrained environments through a comparison of various implementation approaches such as knowledge distillation, pruning, and quantization, with studies achieving a reduction in complexity of up to 97% compared to the unoptimized model. Overall, we conclude that in spite of the availability of lightweight deep learning models, input features, and compression techniques, their integration into low-resource devices, such as microcontrollers, remains limited. Furthermore, more complex tasks, such as general sound classification, especially with expanded frequency bands and real-time operation have yet to be effectively implemented on these devices. These findings highlight the need for a standardised research framework to evaluate these technologies applied to resource-constrained devices, and for further development to realise the wide range of potential applications.

A novel strategy for controllable electrofabrication of molecularly imprinted polymer biosensors utilizing embedded Prussian blue nanoparticles

The reproducibility of ultrasensitive biosensors is vital for clinical research, scalable manufacturing, commercialization, and reliable clinical decision-making, as batch-to-batch variations introduce significant uncertainty. However, most biosensors lack robust quality control (QC) measures. This study introduces an innovative QC strategy to produce highly reproducible molecularly imprinted polymer (MIP) biosensors by leveraging real-time data from the electrofabrication process. Prussian Blue nanoparticles (PB NPs) embedded within the MIP structure enable precise monitoring of surface properties, conductivity, MIP film thickness, and template extraction efficiency. The QC strategy utilizes variations in the current intensity of PB NPs during fabrication to implement real-time, non-destructive QC protocols at critical fabrication stages, minimizing measurement variability and ensuring consistency. This approach was validated by fabricating MIP biosensors for detecting agmatine metabolite and glial fibrillary acidic protein (GFAP) in phosphate-buffered saline (PBS). The QC strategy reduced relative standard deviation (RSD) by 79% for agmatine (RSD = 2.05% QC, RSD = 9.68% control) and 87% for GFAP (RSD = 1.44% QC, RSD = 11.67% control). Moreover, quality-controlled biosensors achieved success rates of 45% for agmatine and 36% for GFAP detection, significantly outperforming bare screen-printed electrodes. This work marks a significant advancement in biosensor development by integrating robust QC protocols directly into the fabrication process. By embedding PB NPs and monitoring electrochemical signals in real-time, this strategy delivers an unprecedented level of reproducibility, scalability, and reliability for MIP biosensors, addressing critical challenges in point-of-care diagnostics and commercial applications.

Implementation of real-time optimal load scheduling for IoT-based intelligent smart energy management system using new decisive algorithm

This paper presents the implementation of a real-time optimal load scheduling system for an IoT-based intelligent smart energy management system (SEMS) using a novel decisive algorithm. The increasing use of electrical equipment by consumers often leads to a mismatch between demand and supply, posing significant challenges to the energy sector. The proposed system addresses these challenges by optimizing load distribution and enhancing energy efficiency through advanced demand-side management techniques. By leveraging real-time data from IoT sensors and incorporating user preferences, the new algorithm dynamically adjusts power consumption to avoid peak-hour overloads, thus preventing widespread power outages. Experimental results demonstrate that the system effectively reduces overall energy consumption while maintaining user comfort and optimizing costs. The innovative approach of controlled partial load shedding based on consumer priorities ensures a balanced and resilient energy supply. This study highlights the potential of IoT and advanced algorithms in transforming energy management practices and providing sustainable solutions for the future.

AI-Powered Digital Twin Technology for Highway System Slope Stability Risk Monitoring

This research proposes an artificial intelligence (AI)-powered digital twin framework for highway slope stability risk monitoring and prediction. For highway slope stability, a digital twin replicates the geological and structural conditions of highway slopes while continuously integrating real-time monitoring data to refine and enhance slope modeling. The framework employs instance segmentation and a random forest model to identify embankments and slopes with high landslide susceptibility scores. Additionally, artificial neural network (ANN) models are trained on historical drilling data to predict 3D subsurface soil type point clouds and groundwater depth maps. The USCS soil classification-based machine learning model achieved an accuracy score of 0.8, calculated by dividing the number of correct soil class predictions by the total number of predictions. The groundwater depth regression model achieved an RMSE of 2.32. These predicted values are integrated as input parameters for seepage and slope stability analyses, ultimately calculating the factor of safety (FoS) under predicted rainfall infiltration scenarios. The proposed methodology automates the identification of embankments and slopes using sub-meter resolution Light Detection and Ranging (LiDAR)-derived digital elevation models (DEMs) and generates critical soil properties and pore water pressure data for slope stability analysis. This enables the provision of early warnings for potential slope failures, facilitating timely interventions and risk mitigation.

Ensemble Classifier for Web Data Scraping with Lexicon Support

An ensemble classifier for web data is used for selective web scraping with lexical support in an innovative way to improving the accuracy and efficiency of data classification from web sources. Web scraping, is a method for obtaining information from webpages, frequently produces massive, unstructured datasets and high risk in data reliability which leads to misuse in communication that are difficult to manage. To overcome this, selective online scraping is used to target certain information important to the classification task, resulting in less noise and higher data quality. The ensemble classifier integrates numerous machine learning models to maximize their strengths, resulting in better overall performance. In this approach, separate classifiers are trained on distinct subsets of scraped data that are chosen based on predetermined criteria utilizing lexicons, which are collections of domain-specific words and phrases. These lexicons guide the selective scraping process, ensuring that only the most relevant data is captured, hence improving classifier accuracy. After scraping and pre-processing the data, the ensemble method aggregates predictions from each classifier, generally using techniques like majority voting, stacking, or weighted average, to get a final classification result. This strategy not only promotes robustness by reducing the risk of overfitting, but it also improves flexibility across other domains by incorporating lexical assistance tailored to specific themes or sectors. The combination of selective web scraping and lexical assistance enables more targeted and resource-efficient data collecting, while the use of an ensemble classifier assures excellent accuracy and reliability in classification tasks. This methodology is especially useful in circumstances where the online data is large, dynamic, and contains a lot of unnecessary or noisy information. The resulting system provides a scalable and effective solution for real-time web data classification, with applications in sentiment analysis, content categorization, and market intelligence.