Real-time Solution Research Articles

Literature Review on Digital Image Processing and Its Techniques

Purpose: Understand the current state of knowledge in the field of digital image processing. Identify key concepts, theories, and methodologies that have been explored in previous research. Explore the various techniques and algorithms used in digital image processing. Evaluate the strengths and weaknesses of existing methods. Identify gaps or limitations in current techniques. Provide a context for the research by summarizing and synthesizing relevant studies. Show how different studies contribute to the overall understanding of digital image processing. Identify gaps in the existing literature that your research can address. Determine areas where further investigation is needed. Offer a foundation for discussion and interpretation of your results in the context of existing literature. Enable you to relate your findings to the broader field of digital image processing. Design/Methodology/Approach: Clearly define the scope of your literature review (e.g., specific techniques, applications, or periods). State the objectives of the literature review, such as identifying trends, evaluating methodologies, or addressing research gaps. Develop a comprehensive search strategy to identify relevant literature. Utilize academic databases, journals, conferences, and other reputable sources. Use a combination of keywords, Boolean operators, and controlled vocabulary (e.g., MeSH terms) to refine search queries. Systematically review and select relevant literature based on the established criteria. Document the process, including databases searched, keywords used, and reasons for inclusion/exclusion. Identify gaps in the existing literature and propose potential avenues for future research. Discuss the implications of these gaps for the advancement of knowledge in the field Findings/Results: Literature often discusses various image enhancement techniques such as histogram equalization, contrast stretching, and spatial filtering. Researchers explore the effectiveness of these techniques in improving image quality for different applications. Segmentation methods, including thresholding, region-based segmentation, and clustering algorithms, are frequently discussed. Object recognition and classification techniques using features like texture, color, and shape are common topics. Different image compression algorithms, such as JPEG, JPEG2000, and various wavelet-based methods, are often compared in terms of compression ratio and quality. The literature might address real-time image processing challenges and solutions, especially in applications like video surveillance, autonomous vehicles, and augmented reality. Originality/Value: Ensure that the literature review comprehensively covers key and recent works in digital image processing. This includes foundational theories, algorithms, and applications. Identify seminal papers, landmark studies, and recent advancements to create a timeline of the field's development. Paper Type: Review of existing literature

Real-Time Motorbike Detection: AI on the Edge Perspective

Motorbikes are an integral part of transportation in emerging countries, but unfortunately, motorbike users are also one the most vulnerable road users (VRUs) and are engaged in a large number of yearly accidents. So, motorbike detection is very important for proper traffic surveillance, road safety, and security. Most of the work related to bike detection has been carried out to improve accuracy. If this task is not performed in real-time then it loses practical significance, but little to none has been reported for its real-time implementation. In this work, we have looked at multiple real-time deployable cost-efficient solutions for motorbike detection using various state-of-the-art embedded edge devices. This paper discusses an investigation of a proposed methodology on five different embedded devices that include Jetson Nano, Jetson TX2, Jetson Xavier, Intel Compute Stick, and Coral Dev Board. Running the highly compute-intensive object detection model on edge devices (in real-time) is made possible by optimization. As a result, we have achieved inference rates on different devices that are twice as high as GPUs, with only a marginal drop in accuracy. Secondly, the baseline accuracy of motorbike detection has been improved by developing a custom network based on YoloV5 by introducing sparsity and depth reduction. Dataset augmentation has been applied at both image and object levels to enhance robustness of detection. We have achieved 99% accuracy as compared to the previously reported 97% accuracy, with better FPS. Additionally, we have provided a performance comparison of motorbike detection on the different embedded edge devices, for practical implementation.

A novel decision support system based on computational intelligence and machine learning: Towards zero-defect manufacturing in injection molding

Real-time monitoring solutions have gained popularity across industries due to the advent of Industry 4.0, AI, and big data enhancing the efficiency of industrial production and equipment decisions. Machine learning models that possess computing intelligence and interpretability provide superior predictive capabilities compared to manual adjustments, resulting in cost savings and manufacturing high-quality products. This study proposes a zero-defect manufacturing decision support system based on computational intelligence feature selection combined with interpretable machine learning. The decision support system integrates Particle Swarm Optimization (PSO) and the C4.5 decision tree method, abbreviated as PSO+C4.5, to enable the continuous monitoring of the injection molding process in real-time, considering production parameter information and collected data quality, guiding the decision-making process for implementing zero-defect manufacturing (ZDM). In contrast to existing research, our innovative methodology relies on computational intelligence techniques for extracting features and employs interpretable machine learning prediction models. In terms of quality prediction, our empirical findings show that the suggested method accomplishes the optimal balance between interpretability and predictive performance (Accuracy: 0.9889, Sensitivity: 0.9869, and Specificity: 0.9935). These characteristics can directly support maintenance personnel and operators in optimizing the processing quality process.

Mechanistic model for the compression strength prediction of masonry columns strengthened with fibre–polymer composites

A mechanistic model is presented for the strength prediction of squared columns made of masonry with a periodic arrangement and strengthened with a fibre–polymer composite jacketing. The formulation is based on an incremental plasticity theory that relies on equilibrium, compatibility, and kinematic equations. The strength domain of brick units and mortar joints is bounded by a multi-surface yield criterion: a Mohr–Coulomb strength domain with a linear cap in compression and a Rankine cut-off in tension. An elasto-plastic response with limited ductility is assumed for both masonry components. Differently, the FRP response is assumed elastic with a brittle failure governed by a limited tensile strain. Phenomenological-based assumptions are undertaken and justified. Details are also provided for the computational implementation of the procedure. The model accuracy is validated against experimental data on masonry squared columns and compared with existing standard-based formulas. Results demonstrate it provides real-time and accurate compressive strength solutions for squared masonry columns with or without a polymer-based wrapping and yet requiring few input parameters for the masonry constituents and reinforcement.

Enhanced-Reach Polarization Optical Time-Domain Reflectometry Technique for Fibre Optical Infrastructure Monitoring

Abstract This interdisciplinary research is focused on constructing and demonstrating enhanced-reach polarization optical time-domain reflectometer (POTDR) for monitoring single-mode fibre optical communication lines. An optical signal state of polarization measurements enables several new possibilities for real-time monitoring solutions in fibre optics. However, there is no commercial equipment available to determine the location in fibre optical cable where the light polarization state changes. The authors present a monitoring technique of an optical signal state of polarization based on reflected signal time-amplitude analysis with improved operation parameters, namely, timing resolution (2 to 3 ps RMS) and amplitude measurement resolution of nanosecond scale pulses (8 to 10 bits) for monitoring of fibre optical communication lines. Additionally, the demonstrated POTDR provides a considerable optical fibre line measurement reach of up to 40 km.

Analysis the improvements of YOLOv5 algorithms: NRT-YOLO, MR-YOLO and YPH-YOLOv5

Computer Vision (CV) is a fundamental aspect of artificial intelligence, with applications spanning multiple domains. The YOLO (You Only Look Once) algorithm has significantly contributed to real-time object recognition in CV. This paper explores the evolution of the YOLO algorithm, focusing on the improvements brought by three specialized variants: NRT-YOLO, MR-YOLO, and TPH-YOLOv5. NRT-YOLO addresses the challenge by introducing the C3NRT module, enhancing precision while maintaining low complexity. MR-YOLO optimizes YOLOv5 for industrial quality control, improving speed and accuracy. TPH-YOLOv5 enhances object detection in drone-captured images by introducing additional prediction heads and transformer modules. Despite these advancements, YOLO algorithms have limitations, including difficulty in detecting small objects and issues in complex scenes. Nevertheless, the research sheds light on the continuous evolution of YOLO algorithms, offering insights into real-time object detection, with applications in manufacturing, healthcare, transportation, and more. The significance of this research lies in showcasing the adaptability and potential of the YOLO framework. As YOLO continues to evolve, it promises to revolutionize various industries and applications, providing robust, real-time object detection solutions.

Leveraging Bit-Serial Architectures for Hardware-Oriented Deep Learning Accelerators with Column-Buffering Dataflow

Bit-serial neural network accelerators address the growing need for compact and energy-efficient deep learning tools. Traditional neural network accelerators, while effective, often grapple with issues of size, power consumption, and versatility in handling a variety of computational tasks. To counter these challenges, this paper introduces an approach that hinges on the integration of bit-serial processing with advanced dataflow techniques and architectural optimizations. Central to this approach is a column-buffering (CB) dataflow, which significantly reduces access and movement requirements for the input feature map (IFM), thereby enhancing efficiency. Moreover, a simplified quantization process effectively eliminates biases, streamlining the overall computation process. Furthermore, this paper presents a meticulously designed LeNet-5 accelerator leveraging a convolutional layer processing element array (CL PEA) architecture incorporating an improved bit-serial multiply–accumulate unit (MAC). Empirically, our work demonstrates superior performance in terms of frequency, chip area, and power consumption compared to current state-of-the-art ASIC designs. Specifically, our design utilizes fewer hardware resources to implement a complete accelerator, achieving a high performance of 7.87 GOPS on a Xilinx Kintex-7 FPGA with a brief processing time of 284.13 μs. The results affirm that our design is exceptionally suited for applications requiring compact, low-power, and real-time solutions.

Optimizing immunization services: A Data Envelopment Analysis (DEA) of child immunization facilities in Pakistan.

Child immunization, though cost-beneficial, experiences varying costs influenced by individual facility-level factors. A real-time solution is to optimize resources and enhance vaccination services through proper method to measure immunization facility efficiency using existing data. Additionally, examine the impact of COVID-19 on facility efficiency, with the primary goal of comprehensively assessing child immunization facility efficiency in Pakistan. Utilizing survey data collected in four rounds from May 2018 to December 2020, the research focuses on doses administered and stock records for the preceding six months in each phase. In the initial stage, Data Envelopment Analysis (DEA) is utilized to compute facility efficiency, employing two models with varied outputs while maintaining consistent inputs. Model 1 assesses doses administered, encompassing three outputs (pentavalent vaccine 1, 2, and 3). Meanwhile, Model 2, focuses on stock used featuring a single output (total doses used). The inputs considered in both models include stock availability, staff members, cold chain equipment, vaccine carriers, and vaccine sessions. The second stage involves the application of two competing regression specifications (Tobit and Simar-Wilson) to explore the impact of the COVID-19 pandemic and external factors on the efficiency of these facilities. In 12 districts across Punjab and Sindh, we assess 466 facilities in Model 1 and 455 in Model 2. Model 1 shows 59% efficiency, and Model 2 shows 70%, indicating excess stock. Stock of vaccines need to be reduced by from 36% to 43%. In the stage, COVID-19 period reduced efficiency in Model 1 by 10%, however, insignificant in Model 2. The proposed methodology, utilizing DEA, emerges as a valuable tool for immunization facilities seeking to improve resource utilization and overall efficiency. Model 1, focusing on doses administered indicates facilities low efficiency at average 59% and proves more pertinent for efficiency analysis as it directly correlates with the number of children vaccinated. The prevalent issue of overstocking across all facilities significantly impacts efficiency. This study underscores the critical importance of optimizing resources through the redistribution of excess stock with low efficiency.

Enhancing dragline operations supervision through computer vision: real time height measurement of dragline spoil piles dump using YOLO

Effective monitoring of spoil pile heights resulting from dragline dumps is critical in mining space management both safely and productively, particularly, during active overburden (OB) removal. This study addresses this concern by replicating stable dump piles in alignment with the dragline balancing diagrams at a dynamic scale, optimizing in-pit volume use. Real-time tracking of dump pile heights ensures efficient dump disposal management, garnering attention in the mining industry. Monitoring dump height and shape during OB disposal near the dragline is vital. It is proposed to employ an experimental setup, consistently dumping specific volume samples from predefined heights at constant velocities. The technique uses You Only Look Once (YOLO) for dump pile height measurements. A benchmark dataset is created, encompassing various dragline dump configurations. YOLO achieves an F1-confidence score of 84.6% and a mean average precision (mAP) value of 99.49% in accurately recognizing dump profiles. To validate its reliability, output is compared with photogrammetry (SFM-MVS and NeRF). Employing 2D computer vision (AI) on simulated video data offers a fast, cost-effective, real-time solution for secure dump pile profile detection and height measurement, enhancing dragline mining efficiency with stable and safe dump heights as per design.

Optimizing Cloud Infrastructure for Real-time AI Processing: Challenges and Solutions

This research paper explores the optimization of cloud infrastructure for real-time artificial intelligence (AI) processing, addressing challenges, solutions, and implications from various perspectives. It discusses scalability issues, latency concerns, resource allocation, security considerations, and cost optimization challenges faced by organizations deploying AI workloads in the cloud. Case studies from diverse industries showcase the tangible benefits of implementing scalable architectures, edge computing integration, specialized hardware utilization, containerization, and data caching techniques. The paper also examines ethical and societal implications, including data privacy, bias, accountability, job displacement, and access disparities. An international perspective highlights regional variations in infrastructure availability, regulatory differences, cultural attitudes, collaboration efforts, and economic impacts. The discussion emphasizes the importance of addressing these challenges while harnessing the economic development opportunities offered by cloud infrastructure optimization for real-time AI processing.

Stay Alert: Drowsiness Detection with IoT Technology

The "Drowsiness Detection using IoT with Eye Blink Sensor and Buzzer" project aims to address the critical issue of driver fatigue and drowsiness, a major cause of road accidents. Leveraging Internet of Things (IoT) technologies and a combination of eye blink sensors and a buzzer, this system provides a real-time solution for monitoring and alerting drivers when signs of drowsiness are detected. The project focuses on enhancing road safety by preventing accidents caused by driver fatigue Drowsiness detection is a critical aspect of ensuring safety, particularly in domains such as transportation where fatigue-related accidents pose significant risks. In recent years, the proliferation of Internet of Things (IoT) devices has enabled innovative approaches to drowsiness detection systems. This abstract outlines a novel framework for drowsiness detection utilizing IoT technologies. Our proposed system integrates various sensors, including facial recognition cameras, heart rate monitors, and accelerometers, into a networked IoT infrastructure. These sensors continuously monitor key physiological and behavioral indicators associated with drowsiness, such as eye movement patterns, blink frequency, heart rate variability, and head position changes.

Closing the Gap on Addiction Recovery Engagement with an AI-infused Convolutional Neural Network Technology Application—A Design Vision

Currently, real-time detection networks elaborate the technical details of the Faster Regional Convolution Neural Network (R-CNN) recognition pipeline. Within existing R-CNN literature, the evolution exhibited by R-CNN is most profound in terms of computational efficiency integrating each training stage to reduce test time and improvement in mean average precision (mAP), which can be infused into an artificially intelligent (AI), machine learning (ML), real-time, interactive, recovery capital application (app). This article introduces a Region Proposal Network (RPN) that shares full-image convolutional features with a real-time detection AI-ML infused network in an interactive, continuously self-learning wrist-wearable real-time recovery capital app for enabling cost-free region proposals (e.g., instantaneous body physiological responses, mapped connections to emergency services, sponsor, counselor, peer support, links to local and specific recovery capital assets, etc.). A fully merged RPN and Faster R-CNN deep convolutional unified network in the app can simultaneously train to aggregate and predict object bounds and objectness scores for implementing recovery capital real-time solutions (e.g., baseball card scoring dashboards, token-based incentive programs, etc.) A continuous training scheme alternates between fine-tuning RPN tasks (e.g., logging and updating personal client information, gamification orientation) and fine-tuning the detection (e.g., real-time biometric monitoring client’s behavior for self-awareness of when to connect with an addiction specialist or family member, quick response (QR) code registration for a 12-step program, advanced security encryption, etc.) in the interactive app. The very deep VGG-16 model detection system has a frame rate of 5fps within a graphic processing unit (GPU) while accomplishing sophisticated object detection accuracy on PASCAL Visual Object Classification Challenge (PASCAL VOC) and Microsoft Common Objects in Context (MS COCO) datasets. This is achieved with only 300 proposals per real-time retrieved data capture point, information bit or image. The app has real-time, infused cartographic and statistical tracking tools to generate Python Codes, which can enable a gamified addiction recovery-oriented digital conscience. Faster R-CNN and RPN can be the foundations of an interactive real-time recovery capital app that can be adaptable to multiple recovery pathways based on participant recovery plans and actions. This paper discusses some of the critical attributes and features to include in the design of a future app to support and close current gaps in needed recovery capital to help those who are dealing with many different forms of addiction recovery.

A Fast and Robust Safety Helmet Network Based on a Mutilscale Swin Transformer

Visual inspection of the workplace and timely reminders of unsafe behaviors (e.g, not wearing a helmet) are particularly significant for avoiding injuries to workers on the construction site. Video surveillance systems generate large amounts of non-structure image data on site for this purpose; however, they require real-time recognition automation solutions based on computer vision. Although various deep-learning-based models have recently provided new ideas for identifying helmets in traffic monitoring, few solutions suitable for industry applications have been discussed due to the complex scenarios of construction sites. In this paper, a fast and robust network based on a mutilscale Swin Transformer is proposed for safety helmet detection (FRSHNet) at construction sites, which contains the following contributions. Firstly, MAE-NAS with the variant of MobileNetV3’s MobBlock as a basic block is applied to implement feature extraction. Simultaneously, a multiscale Swin Transformer module is utilized to obtain the spatial and contexture relationships in the multiscale features. Subsequently, in order to meet the scheme requirements of real-time helmet detection, efficient RepGFPN are adopted to integrate refined multiscale features to form a pyramid structure. Extensive experiments were conducted on the publicly available Pictor-v3 and SHWD datasets. The experimental results show that FRSHNet consistently provided a favorable performance, outperforming the existing state-of-the-art models.

Detection of doxycycline by using a tapered droplet structure fiber sensor.

The abuse of doxycycline (DC) can lead to residues in animals and water environments, which severely threaten human health; however, currently accepted detection methods are generally complicated and cannot be used for real-time detection. Therefore, developing a method for rapid real-time detection of DC microcontent residues is highly important. Herein, based on the Mach-Zehnder interference, we propose a simple tapered droplet structure fiber sensor with a high detection sensitivity. By modifying the sensing region with a molecularly imprinted polymer film of DC, this sensor realizes the specific detection of DC and has a detection sensitivity of 58.81 pm/ppm for DC in a large concentration range of 0-300 ppm. This sensor can be used to detect DC microcontent in aqueous solutions in real time.

Securing patient data in the healthcare industry: A blockchain-driven protocol with advanced encryption.

Ensuring the security and privacy of patient data is a critical concern in the healthcare industry. The growing utilization of electronic data transmission and storage in medical records has amplified apprehensions about data security. However, due to varying stakeholder interests, not all data can be freely shared, necessitating the development of secure protocols. This study presents a highly secure protocol that integrates blockchain technology, patient biometric information, and robust cryptographic algorithms (elliptic curve cryptography (ECC) and advanced encryption algorithm (AEC)) to facilitate data encryption and decryption. The protocol encompasses secure login, secure key sharing, and data sharing mechanisms among miners, offering comprehensive security measures. To validate the effectiveness of the proposed protocol, both informal and formal security analyses are conducted. The security protocol description language in Scyther is utilized to evaluate the protocol's resilience against attacks. The culmination of this research is a secure protocol that leverages blockchain technology and ECC for the secure storage and sharing of medical records. The protocol covers all stages, including system setup, user registration, login mechanisms, key exchange between users and blockchain, communication between blockchains, and interaction with other miners, with a steadfast emphasis on security. Furthermore, the protocol's communication and computation costs are assessed, with a comparison to existing blockchain-based schemes. Informal proofs establish the protocol's security against common attacks faced by medical institutions. Formal simulation of the protocol using the Scyther tool provides definitive evidence of its resistance to attacks. As a result, this protocol presents a viable real-time implementation solution for safeguarding patient data within the healthcare domain, representing a significant contribution to data security.

ENHANCING VEHICULAR NETWORKS WITH DEEP RADIAL BASIS FUNCTION FOR INTELLIGENT TRAFFIC MANAGEMENT

The vehicular networks has spurred research into intelligent traffic management systems to alleviate congestion and enhance safety. However, existing approaches often face challenges in capturing the complex dynamics of urban traffic flow efficiently. In this study, we propose an innovative framework integrating Deep Radial Basis Function (DRBF) networks into vehicular networks for intelligent traffic management. Our approach aims to address the limitations of conventional methods by leveraging the representational power of deep learning while incorporating the flexibility of radial basis function networks. The problem addressed in this research lies in the inadequacy of traditional traffic management systems to adapt to the dynamic nature of urban traffic flow. Existing methods often rely on simplistic models or predefined rules, which may fail to capture the intricate patterns and interactions among vehicles on the road. Consequently, these systems may struggle to provide real-time and accurate traffic management solutions, leading to increased congestion and safety hazards. To bridge this research gap, we propose the integration of DRBF networks, which offer a unique combination of deep learning capabilities and radial basis function interpolation. This hybrid architecture enables the model to learn complex spatial and temporal dependencies from vehicular network data while maintaining computational efficiency and interpretability. By training the DRBF network on historical traffic data and real-time sensor inputs, our methodology can effectively predict traffic flow, identify congestion hotspots, and optimize route recommendations in urban environments. Experimental results on real-world traffic datasets demonstrate the effectiveness of the proposed approach in enhancing traffic management performance. Compared to traditional methods, our DRBF-based framework achieves higher accuracy in traffic flow prediction and generates more efficient routing strategies, leading to reduced travel times and improved overall traffic conditions.

TSFIS-GWO: Metaheuristic-driven takagi-sugeno fuzzy system for adaptive real-time routing in WBANs

Wireless body area network (WBAN) is an internet-of-things technology that facilitates remote patient monitoring and enables medical staff to administer timely treatments. One of the main challenges in designing WBANs is the routing problem, which is complicated due to dynamic changes in network topology and the limited resources of nodes. Several heuristic and metaheuristic methods have been presented to solve the routing problem in WBANs. Although metaheuristics outperform heuristics by producing higher-quality solutions, they cannot respond to real-time requests. This paper introduces a reactive routing protocol for WBANs that combines a fuzzy heuristic with a metaheuristic learning model. It utilizes a Takagi-Sugeno Fuzzy Inference System in conjunction with the Grey Wolf Optimizer (named TSFIS-GWO). The objective is to simultaneously benefit from the advantages of both approaches, namely, the effectiveness of metaheuristics for offline hyperparameter tuning and the quickness of fuzzy heuristics for real-time routing. At every round, the tuned fuzzy system takes multiple parameters of the current state of the nodes and links to construct the multi-hop routing tree under IEEE 802.15.6. To optimize the performance of the protocol for each WBAN, the fuzzy rules of the TSFIS model are automatically adjusted through a learning method based on GWO. This is done in accordance with the specific requirements of the application, and the tuning process takes place once before the protocol is applied. Simulation results in three applications demonstrate that the proposed TSFIS-GWO model is capable of providing real-time solutions while outperforming the existing methods in terms of application-specific performance measures.

Real-time and lightweight detection of grape diseases based on Fusion Transformer YOLO.

Grapes are prone to various diseases throughout their growth cycle, and the failure to promptly control these diseases can result in reduced production and even complete crop failure. Therefore, effective disease control is essential for maximizing grape yield. Accurate disease identification plays a crucial role in this process. In this paper, we proposed a real-time and lightweight detection model called Fusion Transformer YOLO for 4 grape diseases detection. The primary source of the dataset comprises RGB images acquired from plantations situated in North China. Firstly, we introduce a lightweight high-performance VoVNet, which utilizes ghost convolutions and learnable downsampling layer. This backbone is further improved by integrating effective squeeze and excitation blocks and residual connections to the OSA module. These enhancements contribute to improved detection accuracy while maintaining a lightweight network. Secondly, an improved dual-flow PAN+FPN structure with Real-time Transformer is adopted in the neck component, by incorporating 2D position embedding and a single-scale Transformer Encoder into the last feature map. This modification enables real-time performance and improved accuracy in detecting small targets. Finally, we adopt the Decoupled Head based on the improved Task Aligned Predictor in the head component, which balances accuracy and speed. Experimental results demonstrate that FTR-YOLO achieves the high performance across various evaluation metrics, with a mean Average Precision (mAP) of 90.67%, a Frames Per Second (FPS) of 44, and a parameter size of 24.5M. The FTR-YOLO presented in this paper provides a real-time and lightweight solution for the detection of grape diseases. This model effectively assists farmers in detecting grape diseases.

Enhancing Public Transit System Through AI and IoT

The paper investigates the synergy between AI and IoT in revolutionizing public transit systems, emphasizing their role in addressing existing challenges and improving overall efficiency. It explores the application of IoT devices in creating a smart infrastructure that enables real-time data collection, monitoring, and management of transit operations. The research delves into the realm of predictive maintenance, showcasing how AI algorithms, powered by IoT data, can anticipate potential issues in transit vehicles. By analyzing sensor data, transit authorities can proactively address maintenance needs, minimizing downtime, reducing repair costs, and ensuring a more reliable and sustainable public transit service. Route optimization emerges as another crucial aspect of the study, highlighting how AI algorithms leverage historical and real-time data to recommend the most efficient transit routes. Factors such as traffic patterns, weather conditions, and passenger demand are considered to enhance overall system efficiency and reduce travel time for passengers. The paper introduces the concept of dynamic scheduling, illustrating how AI-driven algorithms adapt transit schedules in real-time based on changing passenger needs and external factors. This dynamic approach aims to provide more responsive services, ultimately reducing wait times and improving overall user satisfaction. Passenger information systems are explored as a pivotal component, illustrating how AI and IoT technologies enhance the passenger experience. Real-time communication through mobile apps, digital displays, and other channels ensures that passengers have accurate and timely information about arrival times, delays, and alternative routes, empowering them to make informed decisions. The researchers also delve into fare optimization, examining how AI algorithms analyze data on passenger demographics, travel patterns, and economic factors to create fair and affordable fare structures. This approach aims to encourage ridership, increase revenue, and improve the financial sustainability of public transit systems. The abstract presents a comprehensive overview of how the integration of AI and IoT technologies in public transit systems transforms urban mobility. The findings suggest that leveraging real-time data, predictive analytics, and dynamic solutions can significantly enhance the reliability, accessibility, and sustainability of public transit. As cities continue to explore innovative solutions, the abstract serves as a roadmap for developing smarter, user-friendly, and efficient urban transportation networks, ultimately contributing to improved quality of life for residents.

Real-time high-precision baseline measurement of satellite formation flying based on GNSS

With the establishment of the Chinese space station, a series of space science missions will be conducted in its vicinity. One of the extended tasks for the in-orbit service of space station is the formation flying of small satellites centered around the space station. Satellite formations can perform simultaneous three-dimensional observations of the space station, generating three-dimensional images and monitoring and assessing the status of critical components of the space station. The real-time and accurate relative position measurement is one of the key issues in formation flying. It is a fundamental prerequisite for maintaining and reconfiguring formation configurations, collision avoidance and safety assurance. GNSS-based relative positioning is a low-cost and high-precision measurement method, which is not constrained by light, weather, or relative attitude of satellites. This study introduces a novel approach to determine the relative position of satellites based on single-epoch Global Navigation Satellite System (GNSS) carrier phase difference measurements. Unlike traditional methods, the proposed technique eliminates the need for precise ephemeris and clock bias files and does not require historical observation data. The algorithm avoids the complexity associated with full cycle ambiguity jumps, facilitating real-time, high-precision calculations of relative position baseline vectors. Special attention is given to the influence of Geostationary Earth Orbit (GEO) satellites in the BeiDou Navigation Satellite System (BDS), and measures are taken to mitigate their impact on measurement accuracy by adjusting their observation weights. Our newly developed GNSS-based real-time measurement module, designed for high-quality GNSS signal reception and data communication, was tested on terrestrial and simulated low-orbit platforms. Remarkably, over baselines ranging from 10 m to 9.3 km, while traditional pseudorange differential measurements showed errors up to 1.5571 m, our proposed method consistently held errors under 5 cm and ensured computational speeds within 0.1 s per epoch. High-dynamic zero-baseline tests further validated its potential, with errors less than 1 cm. The innovations encapsulated in this work, resonating with the evolving trends of miniaturized and scalable satellites, present a cost-efficient and real-time solution for inter-satellite relative position measurement. This promises a new horizon in satellite formation technology, with future endeavors focusing on on-orbit experiments.