Real-time Solution Research Articles

Integration of ICT in Agricultural Extension Services: A Review

The integration of Information and Communication Technologies (ICT) into agricultural extension services is transforming the way knowledge and resources are disseminated to farmers, addressing longstanding challenges of reach, efficiency, and inclusivity. Traditional extension systems, constrained by limited resources, outdated methodologies, and poor scalability, often fail to meet the dynamic and diverse needs of modern agriculture. ICT tools, such as mobile phones, internet platforms, Geographic Information Systems (GIS), drones, and emerging technologies like Artificial Intelligence (AI) and blockchain, have revolutionized extension services by providing real-time, location-specific, and cost-effective solutions. This review synthesizes evidence on the role of ICT in enhancing agricultural extension systems, highlighting case studies such as India’s mKisan platform, Africa’s e-Agriculture initiatives, and the global Digital Green project. These examples demonstrate significant improvements in farmer access to timely information on weather, pests, markets, and best practices, leading to increased productivity and resilience.Despite these successes, several barriers impede the widespread adoption of ICT in agricultural extension. A pronounced digital divide, characterized by limited access to smartphones, internet connectivity, and electricity in rural areas, particularly in developing countries, restricts the reach of these innovations. Gender and socioeconomic disparities exacerbate these challenges, with women and marginalized groups often excluded from ICT-enabled benefits. Gaps in digital literacy among farmers and extension workers, inadequate infrastructure, and weak policy support hinder the scalability and sustainability of ICT interventions. Addressing these barriers requires strategic investments in rural connectivity, affordable technology, and capacity-building programs. Policies promoting public-private partnerships, funding for ICT-based innovations, and farmer-centric participatory approaches are critical for long-term success. ICT in agricultural extension include leveraging AI and machine learning for predictive analytics, expanding blockchain use for supply chain transparency, and adopting augmented reality (AR) and virtual reality (VR) for immersive farmer training. The integration of ICT into climate-smart agricultural practices and fostering global collaborations for technology transfer will be pivotal. By addressing challenges and seizing emerging opportunities, ICT can enable equitable, efficient, and sustainable agricultural development, ensuring food security in a rapidly changing world.

Gaussian–Student’s t Mixture Distribution-Based Robust Kalman Filter for Global Navigation Satellite System/Inertial Navigation System/Odometer Data Fusion

Multi-source heterogeneous information fusion based on the Global Navigation Satellite System (GNSS)/Inertial Navigation System (INS)/odometer is an important technical means to solve the problem of navigation and positioning in complex environments. The measurement noise of the GNSS/INS/odometer integrated navigation system is complex and non-stationary; it approximates a Gaussian distribution in an open-sky environment, and it has heavy-tailed properties in the GNSS challenging environment. This work models the measurement noise and one-step prediction as the Gaussian and Student’s t mixture distribution to adjust to different scenarios. The mixture distribution is formulated as the hierarchical Gaussian form by introducing Bernoulli random variables, and the corresponding hierarchical Gaussian state-space model is constructed. Then, the mixing probability of Gaussian and Student’s t distributions could adjust adaptively according to the real-time kinematic solution state. Based on the novel distribution, a robust variational Bayesian Kalman filter is proposed. Finally, two vehicle test cases conducted in GNSS-friendly and challenging environments demonstrate that the proposed robust Kalman filter with the Gaussian–Student’s t mixture distribution can better model heavy-tailed non-Gaussian noise. In challenging environments, the proposed algorithm has position root mean square (RMS) errors of 0.80 m, 0.62 m, and 0.65 m in the north, east, and down directions, respectively. With the assistance of inertial sensors, the positioning gap caused by GNSS outages has been compensated. During seven periods of 60 s simulated GNSS data outages, the RMS position errors in the north, east, and down directions were 0.75 m, 0.30 m, and 0.20 m, respectively.

Algorithms for designing a trajectory of a communication aerial platform for collecting data from wireless sensor network nodes

Algorithms are proposed for solving the problem designing the flight path of a communication aerial platform for collecting monitoring data from the nodes of a large-scale disconnected wireless sensor network to achieve various objective functions: minimizing the collection time or maximizing the network operation time. To achieve the given objective functions, the problem is solved by applying a certain sequence of algorithms: clustering, finding the shortest path and its correction according to the defined heuristics. Obtaining admissible solutions in real time is based on the application of a set of developed algorithms (heuristics), which take into account the relative location of nodes, the energy level of their batteries, and the volume of monitoring data. In order to evaluate the efficiency of the application of flight path construction and data collection algorithms, a corresponding simulation model was developed. The obtained dependences of efficiency indicators (data collection time, battery energy consumption, network operation time) on a set of algorithms for building the spacecraft data collection trajectory with different input data. The results of simulations proved the possibility of reducing data collection time by up to 20 % or increasing network operation time by up to 15 % compared to existing solutions.

Development of AI Model for Robotic Vision Inspection of Sheet-Metal Components in Manufacturing

This paper presents an AI-based robotic vision inspection system designed to enhance quality control in the manufacturing of sheet-metal components. The system integrates a sequential AI model with advanced image processing techniques to automate real-time defect detection and classification. Utilizing a high-resolution camera, the system captures images of components on a conveyor, which are pre- processed using grayscale conversion, Gaussian blurring, and Canny edge detection to emphasize structural details. A deep learning model then classifies isolated regions of interest based on normalized, resized images. Feature matching through ORB (Oriented FAST and Rotated BRIEF) enables accurate alignment with reference templates, while automated measurements convert pixel dimensions to physical units, ensuring reliable detection of deviations. With an average accuracy of 88.3%, the system consistently identifies subtle and complex defects, such as scratches and dimensional deviations, under variable lighting and noise conditions. This AI-driven approach reduces the need for manual inspection, minimizes error, and enhances workflow efficiency, representing a major step toward robust, real-time quality assurance solutions in industrial environments.

AutoMarineWatcher: Real-Time Maritime Surveillance to Detect Threats using YOLO

Maritime security continues to be a significant challenge due to a rise in piracy and helicopter-based hijackings of commercial vessels. While current detection and defense systems focus on large vessels and naval vessels, addressing smaller-scale threats and hijackings remains underexplored. This paper proposes a system called “AutoMarineWatcher,” which is a novel real-time maritime surveillance solution that uses computer vision by leveraging an existing object detection model. The system provides two levels of warnings, allowing crew personnel to observe and initiate subsequent defensive protocols. This allows a reduction in threat response times to enhance security. The system has demonstrated high accuracy by successfully detecting boats, ships, and helicopters. The detections have been successful, and the system proved its effectiveness in both detections and alerts. The performance of the system has been consistent on regular and infrared footage samples. The system ensured the handling of multiple scenarios in regular lighting conditions and low light conditions. The code is available at github.com/Pro-GenAI/AutoMarineWatcher. Keywords: computer vision, real-time surveillance, maritime surveillance, security, early warning, automated alerts

Transforming SME operations with real-time mobile POS and Firebase integration

Small and medium enterprises (SMEs) often struggle to efficiently manage sales transactions and inventory due to a lack of affordable, real-time technological solutions. Existing systems typically fail to offer seamless synchronization and proactive inventory management, which are crucial for resource-constrained businesses. This study addresses these challenges by developing a Mobile Point of Sale (mPOS) application integrated with Firebase, aimed at improving operational performance, reducing data inconsistencies, and supporting decision-making through real-time synchronization. The application was developed using a descriptive research approach, React Native for cross-platform compatibility, and Firebase for its real-time database features. Notable innovations include an automated low-stock notification system and an intuitive user interface for both staff and administrators, designed to streamline inventory management. Comprehensive testing and validation confirmed the system’s reliability, usability, and data consistency. However, the study was limited by its small-scale implementation and the absence of real-world retail trials. Future research should focus on its scalability, integration with advanced analytics, and application in larger retail settings.

Advancements in Arabic Sign Language Recognition: A Method based on Deep Learning to Improve Communication Access

This research anticipates the issue of real-time sign language recognition as a means of facilitating the daily communication of the hearing-impaired persons. Improvement in the rate of real time sign language recognition will help in boosting interaction in the society and access to services for the hearing-impaired persons. This paper outlines a step-by-step guide on fine tuning an object detection model for the AASL using the SSD architecture. The AASL dataset which includes total of 7,857 samples of more than 200 patients are first preprocessed where the images are scaled, normalized, and augmented. In SSD model, the base of the network is the VGG16 network and few extra layers for feature extraction and for auxiliary and prediction of objects are added. Particularly in object detection, Intersection over Union (IoU), and mean Average Precision (mAP) are used in addition to the confusion matrix metrics comprising accuracy, precision, recall, and F1-score. The proposed model provides good recognition accuracy of 98 percent. This feature checks its capability of real-time identification of sign languages and shows 25% efficiency. The efficiency of the proposed method is explained when comparing the results of the modified VGG16-based SSD with other methodologies. As for the improvement of communication for the hearing-impaired individuals, the present work demonstrates that the deep learning methods can be significantly effective; however, suggesting that more research efforts should be directed to real-time solutions and that the datasets should be expanded.

Microelectrode and microchannel integrated micro-robotic arm for bacteria sensing and on-demand drug delivery

Traditional methods such as polymerase chain reaction (PCR) face significant limitations in identifying unknown bacterial targets and in the detection of live multi-strain bacterial coinfections. These methods often fail to offer real-time solutions and precise treatments for diverse bacterial communities present in situ. To address these challenges, we introduce a novel micro-robotic arm system equipped with an integrated sensing electrode and a microchannel. This system combines a scanning electrochemical probe and a microfluidic channel to enable simultaneous biosensing and on-demand drug delivery. The dual functionality of this device successfully addresses the limitations of traditional bacterial identification methods by providing real-time detection and treatment capabilities. Specifically, the technology monitors oxygen levels to detect aerobic bacterial contamination and initiates immediate drug delivery upon detection. The efficacy of this approach was validated using porcine eyeballs, artificial wound samples, and fabric gauzes. The results demonstrate accurate identification of aerobic bacteria and effective pinpointed treatment with a hydrogel-based therapeutic. This innovative method, merging electrochemical sensing with precise drug delivery, presents a significant advancement in managing multi-strain bacterial coinfections, offering a groundbreaking solution to a persistent clinical challenge.

Adversarial Machine Learning In Network Security: A Systematic Review Of Threat Vectors And Defense Mechanisms

Adversarial Machine Learning (AML) has emerged as a critical area of research within network security, addressing the evolving challenge of adversaries exploiting machine learning (ML) models. This systematic review adopts the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) methodology to comprehensively examine threat vectors and defense mechanisms in AML. The study identifies, categorizes, and evaluates existing research focused on adversarial attacks targeting ML algorithms in network security applications, including evasion, poisoning, and model extraction attacks. By rigorously following the PRISMA guidelines, a systematic search across multiple scholarly databases yielded a robust dataset of peer-reviewed articles that were screened, reviewed, and analyzed for inclusion. The review outlines key adversarial techniques employed against ML systems, such as gradient-based attack strategies and black-box attacks and explores the underlying vulnerabilities in network security architectures. Additionally, it highlights defense mechanisms, including adversarial training, input preprocessing, and robust model design, discussing their efficacy and limitations in mitigating adversarial threats. The study also identifies critical gaps in current research, such as the lack of standardized benchmarking for adversarial defenses and the need for scalable and real-time AML solutions.

Can Digital Technology Revolutionize Continuous Education in Diabetes Care?

Rapid technological advancements, such as artificial intelligence, wearable technologies, and telehealth with remote monitoring, are transforming continuous education for health care providers (HCPs) in diabetes management. These technologies improve patient care and necessitate innovative educational approaches to prepare HCPs for clinical integration. Digital education offers real-time, scalable, and cost-effective solutions, especially in areas with health care workforce shortages. However, the effect of digital education on HCPs' knowledge, skills, attitudes, and patient outcomes remains under-researched and necessitates further study. As technologies advance, achieving precision in diabetes continuous education becomes feasible. The 2024 ADA Standards of Care emphasize early adoption of advanced technologies and proficiency among HCPs. This commentary explores transformative trends, discussing limitations and proposing solutions to revolutionize continuous education in diabetes care.

Development And Testing of Arduino Based Autonomous Environmental Monitoring System

This paper presents the development of an Autonomous Environmental Monitoring System (AEMS) designed to track various environmental parameters. With the growing demand for autonomous monitoring systems in today’s modern era, we propose an Arduino-based real-time hardware solution to measure parameters such as flame, temperature, humidity, and distance. The system leverages advanced and cost-effective electronic sensors and hardware to monitor these environmental factors. We developed individual sensor modules for each parameter and integrated them into a unified multi-sensor system through sensor fusion. The collected data is then displayed on a 16 × 2 LCD module. The result is a fully functional autonomous monitoring system, tested under laboratory environmental conditions using a compact, handheld device.

Detecting Fake News Using Data Analytics: A Systematic Literature Review And Machine Learning Approach

This study systematically reviews advancements in fake news detection techniques, examining methodologies and frameworks across machine learning, natural language processing, social network analysis, and multimodal approaches. By following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines, a rigorous and transparent review process was conducted, resulting in the selection and evaluation of 254 research articles. The findings reveal that supervised learning models, such as Support Vector Machines, Decision Trees, and Naïve Bayes, have shown strong performance in text-based fake news classification, particularly when feature selection is optimized. Deep learning models, including CNNs, RNNs, and transformers, have further advanced detection accuracy by capturing complex linguistic patterns, though challenges with computational demands and model interpretability remain. In scenarios with limited labeled data, unsupervised learning models and semi-supervised approaches offer adaptability, with clustering, anomaly detection, and iterative self-labeling proving effective for evolving misinformation. Additionally, cross-disciplinary approaches, integrating insights from psychology, sociology, and network science, enhance detection models by accounting for user behavior, emotional appeal, and social conformity in the spread of fake news. Case studies from collaborative projects underscore the potential of interdisciplinary efforts to develop robust, adaptable detection frameworks. This review concludes that effective fake news detection requires a multifaceted approach, combining technical advancements with social science insights to address the complexity and adaptive nature of misinformation. The study emphasizes the need for continued research in hybrid models and adaptive, real-time detection solutions to strengthen defenses against fake news in diverse digital environments.

Harnessing AI

Integrating digital tools in education is essential for innovative teaching and learning (Msafiri et al., 2023). However, their mere availability does not ensure effective implementation. This presentation explores the development of an AI-powered chatbot designed to assist academics and learning designers in effectively using digital tools. Guided by the Technological Pedagogical Content Knowledge (TPACK) model and the Teaching Enhanced Learning Accreditation Standards (TELAS) framework, this project aims to bridge the gap between tool availability and effective usage. Effective implementation of digital tools begins with human factors, precisely the vision and expertise of educators. To achieve this, the TPACK model highlights three critical domains: technological knowledge, content knowledge, and pedagogical knowledge (Mishra & Koehler, 2006). These domains are critical to the effective and successful implementation of digital tools in the teaching-learning ecosystem. Our AI-powered chatbot leverages the TPACK model to connect educators’ pedagogical and content knowledge by conducting a needs assessment based on user-provided inputs and recommending suitable tools for enhanced teaching and learning. The chatbot interacts with users through precise, conversational inquiries, gathering detailed information on course titles, learning objectives, students' expectations, delivery methods, interaction types, desired tool functionalities, and accessibility considerations. This comprehensive approach ensures the chatbot provides well-informed, contextually relevant responses and resources to the users, thereby enhancing instructional effectiveness. By offering continuous support through our self-enrolled teaching support Canvas site, the chatbot ensures educators have access to assistance when needed, making it particularly beneficial for busy academics and learner designers. This then breaks the traditional barriers of time and place and offers users flexibility and real-time quality digital tool solutions. The chatbot knowledge base is built from a comprehensive tool document that maps each available tool at the [university name] to the TELAS framework. This framework sets rigorous standards and criteria for evaluating the quality of online environments, making it ideal for assessing tools across critical domains, including the online learning environment, learner support, learning and assessment tasks, and learning resources. By configuring this quality resource, the chatbot empowers educators to develop a deeper understanding of effectively integrating technology into their teaching practices for a successful learning experience Additionally, the chatbot provides real-time solutions on available tools, supporting continuous professional development and helping educators stay updated with the latest digital tools for their teaching needs. It offers use cases and knowledge base articles, addressing fragmented knowledge, time constraints, and technical expertise gaps, making it a valuable resource for newly recruited learning designers or academics to easily familiarise and induct themselves in the digital tool space. It offers quality assurance in tool usage by employing the TELAS framework. Moreover, the user data collection can provide insight for organising tailored training and support for academics. In conclusion, this presentation demonstrates the practical application and benefits of our AI-powered chatbot to improve digital tool integration in education. Using the TPACK and TELAS frameworks, the chatbot provides personalised support, helping educators seamlessly incorporate technology into their teaching and offering real-time recommendations to address digital tool challenges. It helps both new and experienced educators enhance their teaching, combining technology, pedagogy, and content knowledge for effective learning.

Fire Fighter Robot Using IOT and Mobile Application

In today's fast-paced world, fire hazards pose significant risks to life, property, and the environment. Traditional fire detection systems often rely on human intervention, leading to delays in response time and exacerbating the damage caused by fire incidents. Our project, the IoT-Based Automatic Fire Detection and Extinguisher Robot, addresses this challenge by utilizing a combination of modern sensor technology, robotics, and IoT to provide an autonomous and real-time solution. The robot is equipped with flame and temperature sensors that allow it to detect fires at an early stage. Once a fire is detected, the robot activates its movement mechanism using DC motors to navigate toward the fire while the integrated servo-controlled water pump precisely sprays water to extinguish the fire. In addition to automatic firefighting, the robot features obstacle detection using ultrasonic sensors, ensuring safe navigation in complex environments. The system includes Bluetooth and Wi-Fi communication, allowing for remote control via an Android mobile app. This app provides both manual and automatic control options and sends real-time fire alerts when the robot detects a fire. This autonomous system minimizes human intervention, speeds up response times, and reduces fire damage effectively. The robot is powered by an ESP32 microcontroller, which processes data from the sensors and controls the motors and water pump. The rescue pod feature allows the robot to perform additional operations like transporting sensitive materials during emergencies. The system's IoT functionality enables real-time alerts and remote monitoring, enhancing its capability as a scalable and cost-effective solution for residential, commercial, and industrial fire safety.

Combatting extensively drug-resistant Salmonella: a global perspective on outbreaks, impacts, and control strategies

ABSTRACT Antibiotic resistance in typhoid fever poses a critical public health problem due to the emergence of extensively drug-resistant (XDR) Salmonella, resulting in prolonged illness and treatment failure. Salmonella enterica serovar Typhi is the most predominant among all serotypes and can acquire resistance. The emergence of XDR Salmonella in various regions globally, particularly Pakistan, presents a concerning trend. However, limited data availability impedes a comprehensive understanding of the outbreaks and hinders the development of real-time solutions. Here, we have provided an updated overview of the current outbreaks of XDR Salmonella in epidemic and endemic regions. Treatments of XDR Salmonella infections are challenging, as there are records of treatment failure in humans and animals. However, intensive prevention techniques can be implemented pending the advent of novel antibiotics. Emphasis on antimicrobial stewardship and frequent surveillance of the pathogen should be made to keep track of potential outbreaks in both human and animal populations. Although progress is being made to combat XDR Salmonella within some regions, a unified and efficient effort on an international scale is required to curtail the XDR outbreak before it escalates and leads us back to the pre-antibiotic era.

Digital Twin Used in Real-Time Monitoring of Operations Performed on CNC Technological Equipment

This article presents the development and implementation of a real-time monitoring solution designed for CNC machines, specifically applied to 150 industrial printing machines, leveraging Digital Twin (DT) technology. The system integrates an SQL database with Android and .NET interfaces, ensuring seamless data synchronization across all machines and optimizing production processes. The real-time monitoring enables immediate reflection of operational changes, enhancing predictive maintenance and reducing machine downtime. A notable feature of the system is its 1 s average data synchronization rate per machine, managing 150 resources distributed over a 10,000 mp area. This fast synchronization improves workflow coordination, reducing production time by approximately 10%, and minimizing operator delays caused by material issues, machine malfunctions, or product defects. The integration of advanced analytics further supports real-time decision-making, predictive maintenance, and performance optimization, aligning the solution with the objectives of Industry 4.0 and Industry 5.0 initiatives. This version reflects the specific results of the research, including the 1 s synchronization rate, the 10% reduction in production time, and the scalability of the system for 150 resources.

AI-Based Controls for Thermal Comfort in Adaptable Buildings: A Review

Due to global weather changes and pandemics, people are more likely to spend most of their time in indoor environments. In this regard, indoor environment quality is a very important aspect of occupant well-being, which is often ignored in modern building designs. Based on our research, thermal comfort is one of the essential items in building environments that can improve the mental stability and productivity of the occupants if the building’s indoor environment is created in a way that meets the occupants’ comfort requirements. Buildings nowadays operate on adaptive or stationary models to attain thermal comfort, which is based on Fanger’s model of the Predicted Mean Vote (PMV). Based on the literature review, limited work has been carried out to enhance the quality of the inside environment, and most research work has been devoted to building energy management. Moreover, there have been no definite solutions so far that have the capability to detect the thermal comfort requirements of multiple occupants in real time. Modern buildings tend to operate on predefined set point parameters to control the indoor environment based on the measured room temperature, which can be different from the thermal comfort requirements of the occupants. This paper discusses the limitations and assumptions that are associated with the existing thermal comfort solutions and emphasises the importance of having a real-time solution to address the thermal requirements of occupants.

A Data Driven Black Box Approach for the Inverse Quantification of Set-Theoretical Uncertainty

Abstract Inverse uncertainty quantification commonly uses the well established Bayesian framework. Recently, alternative interval methodologies have been introduced. However, in their current state of the art implementation, both techniques suffer from a large and usually unpredictable computational effort. Thus, both techniques are not applicable in a real-time context. To achieve a low-cost, real-time solution to this inverse problem, we introduce a deep-learning framework consisting of unsupervised auto-encoders and a shallow neural network. This framework is trained by means of a numerically generated dataset that captures typical relations between the model parameters and selected measured system responses. The performance and efficacy of the technique is illustrated using two distinct case studies. The first case involves the DLR AIRMOD, a benchmark case that has served as reference case for the inverse uncertainty quantification problem. The results demonstrate that the achieved accuracy is on par with the existing interval method found in literature, while requiring only a fraction of its computational resources. The second case study examines a resistance pressure welding process, which is known to require extremely fast monitoring and control due to the high process throughput. Based on the proposed method, and with only a limited selection of simulated responses of the process, it is possible to identify the interval uncertainty of the crucial parameters of the process. The computational cost in this case makes it possible for an inverse uncertainty quantification in a real-time setting.

Advancements in ATM Security for Movement and Tampering Detection: A Review

Advancements in ATM security have become critical due to rising incidents of theft and vandalism. This review aims to evaluate the current state of movement and tampering detection technologies in ATMs, focusing on the integration of advanced machine learning (ML) and deep learning (DL) techniques. Motivated by the need for robust, real-time security solutions, the review addresses limitations in existing systems, such as inadequate anomaly detection and high false-positive rates. The objective is to synthesize advancements in ML and DL methods, including YOLO-based approaches, to enhance ATM security. By examining various methodologies, this review highlights the strengths and weaknesses of different detection systems and proposes directions for future improvements, particularly through the application of the latest YOLO models.

Intelligent assistive obstacle avoidance device based on SLAM and wearable technology

Abstract. This paper presents a conceptual design for an intelligent assistive device that combines visual simultaneous localisation and mapping (SLAM) with wearable technology. The device has been developed through the integration of two innovative fields: visual SLAM and wearable technology. The objective is to develop a device that is both user-friendly and safe. The design addresses the issue of safety for visually impaired individuals when they are outside the home. The objective is to provide a dependable, real-time, and resilient solution that can be utilised in intricate indoor and outdoor settings. The system is designed to provide reliable, real-time, and highly effective solutions in variable environments. The main components of the proposed system include visual SLAM, intelligent wearable devices (as carriers), and a comfortable and straightforward user feedback system (through haptic, auditory, or visual signals to provide feedback to the wearer), while simultaneously considering the safety and comfort of the device. This is due to the consideration of the prolonged and frequent periods of use by visually impaired individuals. This paper considers the latest advances in SLAM algorithms, improvements in wearable sensors and the latest developments in robotics for assisting visually impaired people. It also discusses the potential of these technologies in the future development of assistive devices. The aim is to provide a feasible, comfortable and safe solution that will enhance the safety and autonomy of visually impaired people when they are outside.