Real-time Algorithm Research Articles

Adaptive Energy Management Strategy for Sustainable xEV Charging Stations in Hybrid Microgrid Architecture

Integrating electric vehicles (EVs) into power grids presents critical energy management challenges, especially in microgrid systems powered by renewable energy sources. This study introduces a novel energy management strategy for EV charging stations utilizing an Adaptive Neuro-Fuzzy Inference System (ANFIS) controller. The system dynamically optimizes the coordination of renewable energy sources solar photovoltaic (PV) panels and wind turbines energy storage, and EV chargers. By leveraging real-time data and predictive algorithms, the ANFIS controller adapts to fluctuations in energy supply and demand, ensuring optimal performance. The innovation of this work lies in combining fuzzy logic with neural network-based learning to enhance decision-making under uncertain and variable renewable energy conditions. The proposed approach employs a robust design methodology, integrating neural network training with fuzzy logic system development, to create an adaptive and intelligent control system. Simulation results using MATLAB/Simulink demonstrate a 92% increase in energy efficiency and an 89% enhancement in load-handling capacity compared to conventional methods. The system effectively manages renewable energy variability, battery state-of-charge, and load demand, maintaining stable electrical characteristics even under dynamic wind and solar conditions. This work underscores the importance of advanced AI-driven control strategies in enabling sustainable EV charging infrastructure within microgrid environments.

Application of Slam Technology for Autonomous Mobile Robots in Complex Environments

SLAM technology is widely used in many fields, such as whether it is possible to map the environment and determine the direction of progress while placing a robot in an unknown location in an unknown environment. On this basis, this paper studies the use of autonomous movement of robots in complex environments. This article will first introduce vision technology in dynamic environments and camera-based dynamic environmental sensor technology. Additionally, it will discuss parallel research on real time 3D map optimization and algorithm processing based on cameras. Secondly, the map construction and dynamic maintenance of mobile robots and how to improve the application of Road King tracking algorithm in robots are introduced. Finally, the multi-sensor laser mapping technology and algorithm of mobile robot are introduced. This research will significantly contribute to the development and application of mobile robots capable of processing complex information in challenging environments. The integration of these technologies and algorithms paves the way for more robust and adaptable autonomous navigation systems in real-world applications.

A real-time hyperventilation trend monitoring algorithm in-flight

A real-time hyperventilation trend monitoring algorithm in-flight

드론 영상 활용 딥러닝 기반 피플 카운팅 알고리즘 개발

This study proposes an algorithm that can be utilized in various drone-related fields. The algorithm builds training data based on drone images and applies deep learning to detect and count the objects. The real-time detection algorithm YOLO was used for training, and the results obtained were used to validate object detection performance. To address identification errors, the labeling area was refined, and additional training data containing shadows were collected, whereby an accuracy of more than 90% was achieved. Furthermore, by developing a people counting algorithm, the proposed method can be applied to various fields, such as crowd crush prevention, tracking people’s movements, and access management. In addition, if diverse environments and types of training data are secured, this algorithm can be widely applied to disaster management fields such as searching for missing persons

영상 기반 드론 및 UAM 비상 착륙 알고리즘 개발

In this study, we developed an algorithm that utilizes drone footage to construct training data, applies deep learning techniques for object inference, identifies suitable landing zones, and designates these zones as emergency landing sites. In particular, we developed a drone-based algorithm using YOLO-Seg deep learning to identify emergency landing zones for drones and UAM vehicles. By incorporating diverse training data, the algorithm segments landing areas with an accuracy of 84%-98% under various conditions. For the training process, we employed the YOLO-Segmentation model, which is a real-time object detection algorithm, to achieve precise boundary segmentation for landing zones. This segmentation facilitates accurate area detection and validates the performance of the algorithm. Furthermore, training data captured at different times of the day were incorporated to account for various environmental factors, thereby enhancing the robustness of the algorithm. This versatile algorithm can be applied to a wide range of aerial mobility safety scenarios. The proposed algorithm has demonstrated application potential in diverse and extensive scenarios related to aerial mobility safety.

Development of a fault-tolerant management scheme for on demand real time data centre cloud environment

Fault tolerance in cloud data centers is a critical mechanism for handling the escalating frequency of failures. As the size and complexity of large-scale systems grow, the challenge of predicting and mitigating failures becomes increasingly exponential, rendering previous solutions inadequate for meeting the high-performance demands of both cloud users and providers. This paper aims to address the growing need for improved fault tolerance by developing a management computational intelligence scheme tailored for real-time, on-demand cloud data center environments. In this study, a fault-tolerant computational intelligence scheme was elicited for the parameters necessary for the design. A computational system was also designed to determine league winners based on scheduling checkpoints. Also, the designed system was simulated using java programming language in CloudSim simulation toolkit (3.0.3) with a customized Cloud Analyst Graphic User Interface (GUI) on the Eclipse Integrated Development Environment (IDE) Luna release 4.4. The developed system (Checkpointed League Winner Algorithm) was compared with existing scheme such as Ant Colony Optimization (ACO), Genetic Algorithm (GA) and League Championship Algorithm (LCA) in real time. Checkpointed League Winner Algorithm was also evaluated to check the scheme's resistance to faults and the improvement percentage of the cloud data centres. The parameters used to evaluate the scheme are: failure to perform Ratio (FPR), Failure that causes a Delay in Performance (FDP), and the Rate at which Performance improves (RPI). The result indicates that when the whole average life of each scheme is considered, Checkpointed League Winner Algorithm (CPLWA) results in a 38.2%, 29.9%, and 20.5% improvement over ACO, GA, and LCA, respectively. The average makespan of the scheme indicates that the Checkpointed League Winner Algorithm exhibits a significant improvement, outperforming the ACO, GA, and LCA with 41%, 33%, and 23%, respectively; the response time of the scheme indicates that the Checkpointed League Winner Algorithm outperformed the ACO, GA, and LCA with 54.3%, 56.6%, and 30.2%, respectively; and the failure ratio of the scheme indicates that the Checkpointed League Winner Algorithm performs better than existing meta-heuristics methods (ACO, GA, and LCA) with a lower failure ratio. This improvement can be attributed to the iterative structure, the migration, and the checkpointing approaches employed in the scheme. This study developed a fault tolerance computational intelligence scheme for an on-demand real-time data centre cloud environment in which the Checkpointed League Winner Algorithm outperformed the existing scheme in terms of response time, average makepan and failure ratio. It is then suggested to explore the application of the Checkpointed League Winner Algorithm scheme to address resource management, provisioning, and virtual machine placement challenges within distributed systems.

Integrated strategies for database protection: Leveraging anomaly detection and predictive modelling to prevent data breaches

In the era of digital transformation, safeguarding databases from breaches is critical to maintaining organizational integrity and trust. With the increasing complexity and volume of data, traditional database protection methods are often insufficient to counter sophisticated threats. This paper explores the integration of anomaly detection systems and predictive modelling as a robust strategy to mitigate database vulnerabilities. Anomaly detection systems play a pivotal role in identifying irregular activities, such as unauthorized access or unusual data usage patterns, by leveraging real-time monitoring and machine learning algorithms. These systems are capable of distinguishing between legitimate and malicious behaviours, significantly enhancing early breach detection capabilities. Predictive modelling, using historical breach data, complements anomaly detection by proactively identifying potential vulnerabilities and high-risk areas within database systems. By analysing patterns from past incidents, predictive models enable organizations to anticipate threats and implement targeted security measures. This combined approach not only fortifies databases against attacks but also ensures a proactive defense posture. The paper also presents case studies demonstrating the effectiveness of integrated strategies in real-world scenarios. For instance, organizations employing a dual approach of anomaly detection and predictive modelling have successfully mitigated breaches in critical infrastructures such as financial systems, healthcare databases, and government records. The findings highlight the importance of seamless integration between these methods to achieve a comprehensive security framework. By adopting such advanced strategies, organizations can strengthen their database security, minimize the risk of breaches, and ensure regulatory compliance. This paper underscores the transformative potential of leveraging data-driven technologies for proactive and adaptive database protection.

The Role of Artificial Intelligence in Aviation Construction Projects in the United Arab Emirates: Insights from Construction Professionals

The applications of Artificial Intelligence (AI) in the airport industry are significantly transforming operational efficiency, safety, and passenger experiences. This study investigates the integration of AI within aviation construction projects, with a focus on the United Arab Emirates (UAE). While AI technologies such as facial recognition, IoT, and biometric systems have advanced airport security and operations, their use in construction project management remains limited. A survey was conducted among 101 engineering professionals and experts with experience or involvement in managing aviation-related construction projects. Participants, many of whom had familiarity with AI tools, provided insights into the applicability of AI in areas such as planning, scheduling, and safety monitoring. The majority agreed that AI has the potential to revolutionize project management processes, improving decision-making, and efficiency. AI tools can predict delays, optimize workflows, and enhance safety through real-time data analytics and machine learning algorithms, reducing risks and human error. Despite the UAE’s leadership in AI-driven security advancements, its use in aviation construction is still underdeveloped. This research highlights the potential for broader AI integration across the entire lifecycle of aviation projects. By adopting AI in these areas, UAE airports could set new benchmarks for cost effectiveness, sustainability, and project delivery, reinforcing the region’s status as a leader in technological innovation within the aviation industry.

Real-time fall attitude detection algorithm based on iRMB

Real-time fall attitude detection algorithm based on iRMB

A Real-Time Posture Detection Algorithm Based on Deep Learning

With the development of machine vision and multimedia technology, posture detection and related algorithms have become widely used in the field of human posture recognition. Traditional video surveillance methods have the disadvantages of slow detection speed, low accuracy, interference from occlusions, and poor real-time performance. This paper proposes a real-time pose detection algorithm based on deep learning, which can effectively perform real-time tracking and detection of single and multiple individuals in different indoor and outdoor environments and at different distances. First, a corresponding pose recognition dataset for complex scenes was created based on the YOLO network. Then, the OpenPose method was used to detect key points of the human body. Finally, the Kalman filter multi-object tracking method was used to predict the state of human targets within the occluded area. Real-time detection of human postures (sitting, stand up, standing, sit down, walking, fall down, and lying down) is achieved with corresponding alarms to ensure the timely detection and processing of emergencies.

Real-time fire detection algorithm on low-power endpoint device

Real-time fire detection algorithm on low-power endpoint device

Deep Learning-Based Algorithms for Real-Time Lung Ultrasound Assisted Diagnosis

Lung ultrasound is an increasingly utilized non-invasive imaging modality for assessing lung condition but interpreting it can be challenging and depends on the operator’s experience. To address these challenges, this work proposes an approach that combines artificial intelligence (AI) with feature-based signal processing algorithms. We introduce a specialized deep learning model designed and trained to facilitate the analysis and interpretation of lung ultrasound images by automating the detection and location of pulmonary features, including the pleura, A-lines, B-lines, and consolidations. Employing Convolutional Neural Networks (CNNs) trained on a semi-automatically annotated dataset, the model delineates these pulmonary patterns with the objective of enhancing diagnostic precision. Real-time post-processing algorithms further refine prediction accuracy by reducing false-positives and false-negatives, augmenting interpretational clarity and obtaining a final processing rate of up to 20 frames per second with accuracy levels of 89% for consolidation, 92% for B-lines, 66% for A-lines, and 92% for detecting normal lungs compared with an expert opinion.

Research on Object Detection Based on YOLO and Its Application in Tactile Paving Recognition

The YOLO model, as an advanced real-time object detection algorithm, has made significant progress in the field of object detection since its inception. It achieves fast and accurate object detection by transforming the object detection task into a regression problem and using a single neural network to predict multiple bounding boxes and category probabilities. The YOLO model has significant advantages in processing speed, detection accuracy, and real-time performance, and is widely used in fields such as autonomous driving, intelligent monitoring, and medical image analysis. This paper adopts a tactile paving detection method based on YOLOv8 and CBAM attention mechanism, and improves the model's ability to extract tactile paving features by introducing CBAM attention mechanism and loss function. This method shows good adaptability when dealing with the tactile paving environment under different lighting and weather conditions, can effectively identify diverse obstacles, and provides a strong guarantee for the travel safety of the visually impaired. In conclusion, YOLO model has broad prospects in object detection and tactile paving detection. The tactile paving detection method based on YOLOv8 and CBAM attention mechanism adopted in this paper provides new ideas and methods for the development of tactile paving detection technology, and has important practical application value. In the future, with the continuous optimization of performance and technological innovation of YOLO series models, further improvement of hardware performance, and the fusion of YOLO and other sensor data to form a multimodal detection system, YOLO models are expected to play an important role in more practical application scenarios.

Real-Time Fatigue Detection Algorithms Using Machine Learning for Yawning and Eye State.

Drowsiness while driving is a major factor contributing to traffic accidents, resulting in reduced cognitive performance and increased risk. This article gives a complete analysis of a real-time, non-intrusive sleepiness detection system based on convolutional neural networks (CNNs). The device analyses video data recorded from an in-vehicle camera to monitor drivers' facial expressions and detect fatigue indicators such as yawning and eye states. The system is built on a strong architecture and was trained using a diversified dataset under varying lighting circumstances and facial angles. It uses Haar cascade classifiers for facial area extraction and advanced image processing algorithms for fatigue diagnosis. The results demonstrate that the system obtained a 96.54% testing accuracy, demonstrating the efficiency of using behavioural indicators such as yawning frequency and eye state detection to improve performance. The findings show that CNN-based architectures can address major public safety concerns, such as minimizing accidents caused by drowsy driving. This study not only emphasizes the need of deep learning in establishing dependable and practical driver monitoring systems, but it also lays the groundwork for future improvements, such as the incorporation of new behavioural and physiological measurements. The suggested solution is a big step towards increasing road safety and reducing the risks associated with driver weariness.

Real-Time Postural Disturbance Detection Through Sensor Fusion of EEG and Motion Data Using Machine Learning.

Millions of people around the globe are impacted by falls annually, making it a significant public health concern. Falls are particularly challenging to detect in real time, as they often occur suddenly and with little warning, highlighting the need for innovative detection methods. This study aimed to assist in the advancement of an accurate and efficient fall detection system using electroencephalogram (EEG) data to recognize the reaction to a postural disturbance. We employed a state-space-based system identification approach to extract features from EEG signals indicative of reactions to postural perturbations and compared its performance with those of traditional autoregressive (AR) and Shannon entropy (SE) methods. Using EEG epochs starting from 80 ms after the onset of the event yielded improved performance compared with epochs that started from the onset. The classifier trained on the EEG data achieved promising results, with a sensitivity of up to 90.9%, a specificity of up to 97.3%, and an accuracy of up to 95.2%. Additionally, a real-time algorithm was developed to integrate the EEG and accelerometer data, which enabled accurate fall detection in under 400 ms and achieved an over 99% accuracy in detecting unexpected falls. This research highlights the potential of using EEG data in conjunction with other sensors for developing more accurate and efficient fall detection systems, which can improve the safety and quality of life for elderly adults and other vulnerable individuals.

Bridging Community Engagement and Technological Innovation for Creating Smart and Resilient Cities: A Systematic Literature Review

Urbanization presents significant challenges to disaster management as cities grow and develop, hence increasing their vulnerability to disasters. Disaster resilience is crucial for protecting lives and infrastructure, ensuring economic stability, promoting equality and cohesion, and ensuring the long-term viability of metropolitan regions in these rapidly growing cities. This paper investigates contemporary approaches to creating smart and resilient urban environments through disaster management that emphasize community-based solutions in prioritizing advanced technologies. The key findings of the research include three factors to be accomplished in utilizing technology in community-based disaster management, trust in the crowd, digital divide, and cultural sensitivity. Moreover, the review highlights the significance of the use of smart technologies in improving urban resilience, including but not limited to real-time data-sharing platforms and ML algorithms. Furthermore, it emphasizes the challenges regarding reliability and accuracy in crowdsourced information, stressing the importance of user awareness.

Enhancing supply chain resilience through artificial intelligence: Analyzing problem-solving approaches in logistics management

In an increasingly complex and unpredictable global economy, supply chain resilience has emerged as a critical priority for organizations striving to adapt to disruptions and maintain operational continuity. Artificial intelligence (AI) has proven to be a transformative force in addressing the challenges of logistics and supply chain management, offering innovative solutions for forecasting, decision-making, and operational efficiency. This research explores how AI-driven approaches can solve specific supply chain challenges, including demand variability, disruption management, inventory optimization, transportation inefficiencies, and supplier relationship management. The review proposes a comprehensive analysis of AI technologies such as predictive analytics, real-time monitoring systems, optimization algorithms, and autonomous systems, highlighting their contributions to enhancing supply chain resilience. By leveraging AI, organizations can improve their ability to predict disruptions, optimize resource allocation, and respond dynamically to real-time challenges. The research incorporates case studies and real-world applications to illustrate successful implementations of AI in logistics, as well as lessons learned from failed attempts. Additionally, the review examines the benefits of integrating AI into supply chain operations, such as improved risk management, enhanced decision-making, and increased adaptability to uncertainties. However, it also addresses the challenges of AI adoption, including high implementation costs, data privacy concerns, and organizational resistance to change. By presenting actionable insights and recommendations, this research aims to provide a roadmap for organizations seeking to harness AI to strengthen their supply chain resilience. The findings underscore the transformative potential of AI technologies in fostering robust, adaptive, and efficient supply chain systems capable of withstanding future uncertainties and disruptions. Keywords: Supply Chain, Artificial Intelligence, Logistics Management, Review.

Enhancing No Reference Laparoscopic Video Quality Assessment with Evolutionary ANFIS

Abstract Distortions in laparoscopic videos affect surgeon visibility and surgical precision, underscoring the need for sustained high video quality. This study presents a real-time laparoscopic video quality assessment algorithm independent of reference content availability. Statistical parameters derived from luminance, local binary pattern and motion-vector maps of video frames are observed to effectively discern distortion types and severities. These parameters are used to train an evolutionary adaptive neuro-fuzzy inference system (ANFIS) end-to-end with subjective score labels. Training and validation loss curves saturate at the 85th epoch, demonstrating the model’s efficient data fitting capability. Performance comparison with other state-of-the-art methods reveals superior results, with high correlation scores of 0.9989 and 0.9446 for experts and 0.9956 and 0.9847 for non-experts, alongside low root mean square errors of 0.0828 and 0.1685 for expert and non-experts, respectively. The model accurately replicates the expert and non-expert perceptual opinions, encouraging future research in stereoscopic, augmented, and virtual reality data.

SAM: Semi-Active Mechanism for Extensible Continuum Manipulator and Real-Time Hysteresis Compensation Control Algorithm.

Cable-driven continuum manipulators (CDCMs) enable scar-free procedures but face limitations in workspace and control accuracy due to hysteresis. We introduce an extensible CDCM with a semi-active mechanism (SAM) and develop a real-time hysteresis compensation control algorithm using a temporal convolution network (TCN) based on data collected from fiducial markers and RGBD sensing. Performance validation shows the proposed controller significantly reduces hysteresis by up to 69.5% in random trajectory tracking test and approximately 26% in the box pointing task. The SAM mechanism enables access to various lesions without damaging surrounding tissues. The proposed controller with TCN-based compensation effectively predicts hysteresis behaviour and minimises position and joint angle errors in real-time, which has the potential to enhance surgical task performance.

Adaptive Learning Systems: Harnessing AI to Personalize Educational Outcomes

This paper explores the transformative power ofAdaptive Learning Systems powered by Artificial Intelligence(ALS) to personalize educational outcomes for diverse learners in a way that adaptive learning approaches have the advantage of meeting the needs of the student’s learning style and pace, which traditional education methods have failed to do. It uses data analytics and machine learning algorithms in real time to tailor content and assessment to the specific needs of each learner. In our work, we break down mechanisms by which AI enables timely feedback, changes learning paths, and raises engagement that makes for a more effective and inclusive learningenvironment. Based on case studies and empirical analysis, the contribution of this research will show the added values and challenges AI adaptive learning solutions bring to different educational settings. The findings put so much importance on continuous assessment, hence integrating and harnessing pedagogical best practices for the maximization of AI effect on personal learning.