Real-Time Targeting and Trajectory Estimation for Enhanced Network Centricity

This paper presents an experimental and scientifically driven facility at NATO STO CMRE, called GliderC2 in this publication. The key aspects of its data flow for remotely operating a fleet of unmanned underwater gliders (UUGs) deployed at sea / in the ocean is presented. Interoperable standards are used to disseminate live UUG positions in near real-time, as well as their collected data and the processed information (e.g. added value products, such as oceanographic forecasts). All this information is provided to other Command and Control (C2) and Common Operational Picture (COP) capabilities. Results are shown from a live test during the live CMRE sea-trial LOGMEC16 (Long-term Glider Missions for Environmental Characterization 2016) in the Ligurian Sea (Italy), where several UUGs were deployed and operated for two consecutive months (May and June) in 2016. Live UUG positions, collected data and processed information were provided in near real-time to other C2 and COP capabilities during the NATO Coalition Warrior Interoperability Exercise (CWIX) 2016, at the NATO Joint Force Training Center (JFTC), Poland. Visual results are provided for the dissemination of such information, as well as estimates of the times needed to provide and visualize live UUG positions and data. Ideas for further work are provided at the end of this paper, stimulating the continuation of this work.

Prediction of various parameters in the agriculture field using sensors is a significant topic nowadays. However, in many scenarios, the sensor data does not accurately detect the real parameter(/s) in the agriculture field. The sensor data may vary due to various external factors, whereas the real parameters don’t vary too much for a particular agriculture field. The present work introduces a modified neural network approach to predict real agricultural parameters from sensor data with accuracy caused by several external factors and demonstrates enhanced predictive accuracy and adaptability. The neural network takes the sensor data as input in various weather conditions and tries to find out the original real parameters of that sensor data. The real-time sensor data was collected from multiple agricultural sites. The results demonstrated high predictive accuracy, with the neural network outperforming traditional statistical methods in forecasting soil moisture and other vital variables. Additionally, the model’s ability to generalize across different environmental conditions enhances its applicability in various crop management scenarios. The study concludes that neural networks hold significant potential for improving the efficiency of smart agriculture systems by providing timely, data driven insights for farmers and agronomists. Further research will explore the integration of deep learning models and edge computing to enhance scalability and realtime responsiveness in field applications. The aforementioned research highlights the significance of NPK sensors in sustainable farming methods, namely in enabling accurate nutrient management via real-time data.

The evolution of the Internet of things and the continuing increase in the number of sensors connected to the Internet impose big challenges regarding the management of the resulting deluge of data and network latency. Uploading sensor data over the web does not add value. Therefore, an efficient knowledge extraction technique is badly needed to reduce the amount of data transfer and to help simplify the process of knowledge management. Homoscedasticity and statistical features extraction are introduced in this paper as novelty detection enabling techniques, which help extract the important events in sensor data in real time when used with neural classifiers. Experiments have been conducted on a fog computing platform. System performance has been also evaluated on an occupancy data set and showed promising results.

This paper describes a novel switched-capacitor design for the implementation of artificial neural networks in VLSI using the pulse-stream signalling mechanism and dynamic weight storage. Test results are presented from a small number of chips, paying particular attention to the synaptic weight linearity and storage time. The synaptic weights are fully-programmable and the VLSI chips can be used to process analogue sensor data in real time with an accuracy equivalent to 6 or 7 bits, as demonstrated in the robotics application described in the paper.

To make roads safer, we need new ways to test driving skills and make transportation systems better than ever. This study presents an Intelligent Driving Assessment System that uses multiple sensors to track important driving metrics in real time. The device checks the driver's skill by looking at how much pressure they put on the accelerator pedal. When you combine data from several sensors, you get a full picture of how a driver acts and performs. The pressure on the accelerator pedal shows how well the driver controls the throttle and how quickly they speed up, which are both important for judging driving skill and fuel efficiency. The driver's alertness and focus are tracked by sensors that watch for blinking. The MEMS sensor steering control study also looks at how well drivers stay in their lanes and how safe their cars are. Advanced AI algorithms use machine learning to look at and understand sensor data in real time to judge each driving trait. These algorithms look at a driver's past driving habits, the weather, and how traffic changes to make a personal and accurate judgment of their performance. The AI-powered system combines data from many sensors to give a percentage score for safer driving and licensing choices. A system like this could help both AZS drivers and society as a whole. The technology lets drivers know how good they are at driving by showing them where they need to improve and making them more aware of their own driving. People who use the road more responsibly and safely are those who are watched and given feedback all the time. The system helps transportation and regulatory agencies check how well people can drive, give out licenses, and make sure safety standards are followed in a fair and systematic way.

In this paper we present a novel algorithm for estimating system parameters of arbitrary aerial manipulators. We abstract an aerial manipulator as a rigid body with forces and torques applied at arbitrary locations. It is also assumed that there are sensors that measure forces, accelerations and angular velocities at these locations. The problem studied here is to fuse these sensor data in real time to estimate mass, location of center of gravity, moment of inertia matrix and the locations where these forces are applied. We analytically derive expressions that relate these quantities to the sensor data instantly or over consecutive samples. We also characterize the motion of the manipulator for which such estimates are impossible to obtain. This characterization allows us to define maneuvers for the aerial manipulator for which we can always determine the rigid body parameters. The algorithm is successfully demonstrated on a quad-rotor system with a moving arm, which causes real-time variation in the inertia matrix and the center-of-gravity location.

Computational methods for automatic target recognition are constrained by the need to analyze increasingly high-dimensional sensor data in real time. Parallel processing has the potential to speed up computational bottlenecks in many automatic target recognition (ATR) methods. We will implement parallelized versions of target tracking methods and discuss gains in algorithm completion time.

The primary objectives of this paper are to test an adaptive sampling method for an autonomous underwater vehicle, specifically tailored to track a hydrocarbon plume in the water column. An overview of the simulation of the developed applications within the autonomous system is presented together with the subsequent validation achieved through field trials in an area of natural oil seeps near to Scott Inlet in Baffin Bay. This builds upon our prior published work in methodological development. The method employed involves an integrated backseat drive of the AUV, which processes in situ sensor data in real time, assesses mission status, and determines the next task. The core of the developed system comprises three modular components—Search, Survey, and Sample—each designed for independent and sequential execution. Results from tests in Baffin Bay demonstrate that the backseat drive operating system successfully accomplished mission goals, recovering water samples at depths of 20 m, 50 m, and 200 m before mission completion and vehicle retrieval. The principal conclusion drawn from these trials underscores the system’s resilience in enhanced decision autonomy and validates its applicability to marine pollutant assessment and mitigation.

Traditional manual and drone coating maintenance methods have problems such as low efficiency, high risk, and uneven spraying, which are difficult to meet the operation and maintenance needs of offshore wind farms. To address this challenge, this study proposed an intelligent operation platform that integrates a tracked vacuum adsorption mobile chassis, multi-sensor fusion and hierarchical control system. The robot system uses Jetson Nano as the main control device (equipped with the EfficientDet-D7x model), combined with the STM32F103ZET6 auxiliary control unit to achieve full-process coordination of damage detection, motion control and spray repair. Among them, Jetson Nano has 128 The GPU acceleration capability of the CUDA core achieves 98.7% mAP accuracy (48 FPS) in blade damage detection, which is a significant performance improvement over the Raspberry Pi (85% mAP, 12 FPS); the crawler vacuum adsorption chassis optimizes motion control through the fuzzy PID algorithm, increasing the response speed by 30.5%. Combined with the vacuum pump to dynamically adjust the adsorption force, it can move stably on the slippery and tilted blade surface; the STM32 unit processes IMU and ultrasonic sensor data in real time, and interacts efficiently with Jetson Nano through the UART protocol to ensure the accuracy of the robot arm's spray path planning.

PurposeThe study aims to propose an intelligent real-time traffic model to address the traffic congestion problem. The proposed model assists the urban population in their everyday lives by assessing the probability of road accidents and accurate traffic information prediction. It also helps in reducing overall carbon dioxide emissions in the environment and assists the urban population in their everyday lives by increasing overall transportation quality.Design/methodology/approachThis study offered a real-time traffic model based on the analysis of numerous sensor data. Real-time traffic prediction systems can identify and visualize current traffic conditions on a particular lane. The proposed model incorporated data from road sensors as well as a variety of other sources. It is difficult to capture and process large amounts of sensor data in real time. Sensor data is consumed by streaming analytics platforms that use big data technologies, which is then processed using a range of deep learning and machine learning techniques.FindingsThe study provided in this paper would fill a gap in the data analytics sector by delivering a more accurate and trustworthy model that uses internet of things sensor data and other data sources. This method can also assist organizations such as transit agencies and public safety departments in making strategic decisions by incorporating it into their platforms.Research limitations/implicationsThe model has a big flaw in that it makes predictions for the period following January 2020 that are not particularly accurate. This, however, is not a flaw in the model; rather, it is a flaw in Covid-19, the global epidemic. The global pandemic has impacted the traffic scenario, resulting in erratic data for the period after February 2020. However, once the circumstance returns to normal, the authors are confident in their model’s ability to produce accurate forecasts.Practical implicationsTo help users choose when to go, this study intended to pinpoint the causes of traffic congestion on the highways in the Bay Area as well as forecast real-time traffic speeds. To determine the best attributes that influence traffic speed in this study, the authors obtained data from the Caltrans performance measurement system (PeMS), reviewed it and used multiple models. The authors developed a model that can forecast traffic speed while accounting for outside variables like weather and incident data, with decent accuracy and generalizability. To assist users in determining traffic congestion at a certain location on a specific day, the forecast method uses a graphical user interface. This user interface has been designed to be readily expanded in the future as the project’s scope and usefulness increase. The authors’ Web-based traffic speed prediction platform is useful for both municipal planners and individual travellers. The authors were able to get excellent results by using five years of data (2015–2019) to train the models and forecast outcomes for 2020 data. The authors’ algorithm produced highly accurate predictions when tested using data from January 2020. The benefits of this model include accurate traffic speed forecasts for California’s four main freeways (Freeway 101, I-680, 880 and 280) for a specific place on a certain date. The scalable model performs better than the vast majority of earlier models created by other scholars in the field. The government would benefit from better planning and execution of new transportation projects if this programme were to be extended across the entire state of California. This initiative could be expanded to include the full state of California, assisting the government in better planning and implementing new transportation projects.Social implicationsTo estimate traffic congestion, the proposed model takes into account a variety of data sources, including weather and incident data. According to traffic congestion statistics, “bottlenecks” account for 40% of traffic congestion, “traffic incidents” account for 25% and “work zones” account for 10% (Traffic Congestion Statistics). As a result, incident data must be considered for analysis. The study uses traffic, weather and event data from the previous five years to estimate traffic congestion in any given area. As a result, the results predicted by the proposed model would be more accurate, and commuters who need to schedule ahead of time for work would benefit greatly.Originality/valueThe proposed work allows the user to choose the optimum time and mode of transportation for them. The underlying idea behind this model is that if a car spends more time on the road, it will cause traffic congestion. The proposed system encourages users to arrive at their location in a short period of time. Congestion is an indicator that public transportation needs to be expanded. The optimum route is compared to other kinds of public transit using this methodology (Greenfield, 2014). If the commute time is comparable to that of private car transportation during peak hours, consumers should take public transportation.

Two fundamental problems in olfactory signal processing is the large time constant and the large variance in the odor receptor code. Depending on the sensing technology and the analyte under investigation, obtaining a steady-state pattern from a sensor array may take minutes, yet still be unreliable. Therefore, odors are encoded in a spatio-temporal fashion in the nature, a task that fits very well in Cellular Neural Network (CNN) paradigm. Inspired by the generic insect olfactory system, we propose a CNN-based signal conditioning system that can be directly applicable on raw sensor data in real time. We interface the system with a Support Vector Machine (SVM) classifier, which maps the dynamically-encoded odor to an identity, and demonstrate the recognition system on a dataset recorded from a metal-oxide odor sensor array.

Objectives/Scope: Traditionally Daily Drilling Reports were used as the main source of the data input for Invisible Lost Time calculations with great success. One observed drawback was that the hidden causes that lead to invisible lost time were not identified. This paper outlines the framework to incorporate Real-Time high frequency rig-floor sensor data in the invisible lost time calculation, identification, and reduction exercises. This approach breaks down, downhole activities into smaller, measurable, discrete sub-activities that are measured, benchmarked, and targeted for improvement. Methods, Procedures, Process: This paper covers three major downhole activities: Drilling, Tripping, and Running Casing, breaking them down into thirty-three sub-activities. A three-year drilling activities dataset is categorized into comparable groups based on drilling rig capabilities and formation characteristics. The sub-activities are then presented on a histogram with the average, P10, P50, and P95 values of each sub-activity determined based on a pre-accepted category. This benchmarking process enabled the generation of the targets that are currently being used for calculating and understanding the invisible lost time causes in the operation. Results, Observations, Conclusions: revious reporting would simply identify the phase of operation that is creating the invisible lost time. Complementing the existing Invisible Lost Time calculation model with Real-Time data has enabled the understanding of the operational steps that lead to sub-optimal performance. A good example of this would be the drilling phase. The new approach is able to pinpoint the steps in the drilling phase that generates the invisible lost time, for example when post-connection times are excessively exceeding historical norms. Another advantage is the ability to run the report in the middle of the activity and highlight that the current rate of execution is not optimal. This enables the supervisor to investigate the situation and propose solutions to improve performance on the ongoing activity. In addition, this approach has been used successfully for ranking the performance of casing running service companies and helping in the decision-making process for awarding new contracts.

Over recent years, the frequency and intensity of fire disasters have escalated, underscoring the urgent need for accurate and timely disaster classification and mitigation strategies. The proposed approach integrates fine-tuned deep learning models with real-time sensor data and digital twin technology to enhance fire disaster detection and early mitigation capabilities. This methodology leverages diverse data sources, including real-time Internet of Things (IoT) sensor readings, satellite imagery, and historical fire incident data. Advanced deep learning architectures such as convolutional neural networks (CNNs), deep CNNs (DCNNs), and recurrent neural networks (RNNs) are utilized to identify critical spatial and temporal patterns in the data. The models are trained on a comprehensive dataset encompassing environmental indicators, fire-prone area characteristics, and real-time meteorological data. A key innovation is the use of digital twin technology, which dynamically integrates real-time data from IoT sensors and simulation models to predict fire disaster scenarios accurately. The integration of digital twins enables continuous monitoring and virtual replication of physical systems, facilitating proactive decision-making and early warnings. This real-time assimilation enables proactive decision-making and resource allocation tailored to diverse geographical and socio-economic contexts. Performance evaluations reveal that the DCNN+Digital twin framework achieves a 99% classification accuracy with a reduced error rate of 3% over 500 runs, outperforming standalone models, such as RNN (90% accuracy, 10% error), CNN (96% accuracy, 8% error), and DCNN (97% accuracy, 6% error). The proposed approach offers a transformative solution to fire disaster management, promoting community resilience, environmental sustainability, and effective mitigation strategies in the face of escalating fire risks.

Increasing use of smartphones with control systems and wireless sensor networks is in mainstream. Among this scenario, internet of things emerges to connect real-time objects like smartphones, sensors and actuators to the internet, providing communication among them and facilitating mobility. This paper focuses on android operating system-based Bluetooth serial port profile (SPP) application - My Smart BT. It collects the real-time sensor data from connected controller interfaced with application specific sensors, displays the data on the screen and streams the data to the server simultaneously. Wireless internet connections and Bluetooth are used for real-time data transmissions between the connected devices. For testing purpose, light sensor, motion sensor and SPP Bluetooth module are interfaced with Intel Galileo Gen 2-based testbed to interpret the real-time sensor data. Besides, PHP-based central MySQL server database is used for real-time data storage and graphical analysis. Application is evaluated by different segment of users.

The Autonomous Multichannel Acoustic Recorder (AMAR, JASCO Applied Sciences) is a sophisticated precision instrument for passive acoustic monitoring and accurate underwater sound level measurements. It can be integrated with small hydrophone arrays and non-acoustic oceanographic sensors. To date, AMARs have typically been used autonomously and deployed for a few months to a year on oceanographic moorings; however, AMARs are also capable of real-time data streaming when connected to a data telemetry system. This paper describes the capabilities and functionality of the AMAR through the example of its integration within Ocean Networks Canada's VENUS Ocean Observatory deployed off the coast of British Columbia, Canada. The recent deployment of two AMAR-based hydrophone arrays and associated non-acoustic and oceanographic sensors within the VENUS system is presented in detail. The planned research and development within the AMARs on VENUS program, as well as preliminary results on the real-time automatic detection, classification, localization, and tracking of marine mammals, are presented. The two AMARs deployed on the VENUS Ocean Observatory demonstrate that, unlike traditional underwater acoustic recorders, the AMAR can act as a hub for mini ocean observatories, capturing and transmitting both acoustic and non-acoustic sensor data in realtime. It is demonstrated that the AMAR is an effective technology that can be used in near-shore, small-scale, low-cost ocean observatories.