Real Time Computing

This paper explores a novel correlation between prime numbers and nuclear synthesis, proposing a theory where primes form the foundation of nuclear fusion and elemental abundance in the universe. By simulating fusion and fission using prime number based rules, we demonstrate a correlation between our model and observed isotopic abundances. This suggests a potential framework for understanding nuclear processes and the evolution of the cosmos.

Traffic light breakdown is very common. These create hassle as well as unsafe condition for road users. This project provides a new paradigm in traffic light monitoring system. The system has the capability to send multiple Short Message Service (SMS) to the contractor, traffic police and local council in the event of a malfunction traffic light. Normally, road users have to call the contractor based on the information displayed at the traffic light pole. With the current system, time taken to respond to the traffic light breakdown depends on how soon road users call the contractor. Monitoring system for fault traffic light will address this matter. In this project, the system can detect two types of failure, power failure and bulb/ Light Emitting Diode (LED) failure (a particular light not working i.e. red light only). Upon receiving the power failure signal, SMS will be sent to the above-mentioned parties for further action. For LED types of traffic light, the system has the capab...

This paper describes the development of a multi-robot system for Area Reduction in Humanitarian Demining. In spite of the specific requirements imposed to the work being carried out by the Humanitarian Demining domain, the results being achieved can also be used in other domains such as surveillance and remote monitoring. A multi-agent based architecture is responsible for coordinating a progressive stochastic analysis of the terrain. The all-terrain navigation used by the mobile robots is attained by a novel embodied reactive obstacle avoidance method. A Control Mission software has been developed to plan, configure and supervise the operations. Highly compliant legged and wheeled platforms have been developed accomplishing low-cost all-terrain robots. Digital signal processing algorithms have been applied for landmine detection using the payload sensors.

This paper describes the development of a multi-robot system for Area Reduction in Humanitarian Demining. In spite of the specific requirements imposed to the work being carried out by the Humanitarian Demining domain, the results being achieved can also be used in other domains such as surveillance and remote monitoring. A multi-agent based architecture is responsible for coordinating a progressive stochastic analysis of the terrain. The all-terrain navigation used by the mobile robots is attained by a novel embodied reactive obstacle avoidance method. A Control Mission software has been developed to plan, configure and supervise the operations. Highly compliant legged and wheeled platforms have been developed accomplishing low-cost all-terrain robots. Digital signal processing algorithms have been applied for landmine detection using the payload sensors.

The advent of Low Power Wide Area Networks (LPWAN) has enabled the feasibility of wireless sensor networks for environmental traffic sensing across urban areas. In this study, we explore the usage of LoRaWAN end nodes as traffic sensing sensors to offer a practical traffic management solution. The monitored Received Signal Strength Indicator (RSSI) factor is reported and used in the gateways to assess the traffic of the environment. Our technique utilizes LoRaWAN as a long-range communication technology to provide a largescale system. In this work, we present a method of using LoRaWAN devices to estimate traffic flows. LoRaWAN end devices then transmit their packets to different gateways. Their RSSI will be affected by the number of cars present on the roadway. We used SVM and clustering methods to classify the approximate number of cars present. This paper details our experiences with the design and real implementation of this system across an area that stretches for miles in urban scenarios. We continuously measured and reported RSSI at different gateways for weeks. Results have shown that if a LoRaWAN end node is placed in an optimal position, up to 96% of correct environment traffic level detection can be obtained. Additionally, we share the lessons learned from such a deployment for traffic sensing.

We consider a status update system consisting of a sampler, a controller, a processing unit, a transmitter, and a sink. The sampler generates a sample upon receiving a request from the controller and the sample requires further processing before transmission, hence is computation-intensive. This is mathematically modeled by a server called process server. After processing the sample, the status update packet is generated and sent to the transmitter for delivery to the sink. This is mathematically modeled by a server called transmit server. The service time of each packet at the transmit and process servers follow geometric distributions. Moreover, we consider that the servers serve packets under the blocking policy, i.e., whenever a server is busy at the arrival time of a new packet, the new arriving packet is blocked and discarded. We analyze the average age of information (AoI) for two fixed policies, namely, 1) zero-wait-one policy and 2) zero-wait-blocking policy. According to the former policy, the controller requests sampling when there is no packet in the system. According to the zero-waitblocking policy, the controller requests a sample whenever the process server is idle. Furthermore, we develop an optimal control policy to minimize the average AoI using the tools of Markov decision process (MDP). In numerical results, we evaluate the performance of the policies under different system parameters. Moreover, we analyze the structure of the optimal policy.

Indoor Positioning Systems (IPSs) are used to estimate the position of mobile devices in indoor environments. Fingerprinting is the most used technique because of its higher accuracy. However, this technique requires a labor-intensive training phase that measures the Received Signal Strength Indicator (RSSI) at all Reference Points (RPs) locations. On the other hand, model-based IPSs use signal propagation models to estimate distances from RSSI. Thus, they do not require expensive training but result in higher positioning errors. In this work, we propose SynTra-IPS (Synthetic Training Indoor Positioning System), a hybrid approach between a fingerprint and a model-based IPS that uses synthetic, simulated datasets combined with data fusion techniques to eliminate the fingerprint collection cost. In our solution, we use the map of the scenario, with known anchor nodes' positions and the log-distance signal propagation model, to generate several synthetic, model-based, fingerprint training datasets. In the online phase of our solution, the positions estimated by the several synthetic datasets using K-Nearest Neighbors (KNN) are combined using data fusion techniques into a single, more accurate position. We evaluated the performance of our SynTra solution in a real-world, large-scale environment using mobile devices with Bluetooth Low Energy (BLE) technology, and we compared our solution to classic approaches from the literature. Our results show that SynTra can locate mobile devices with an average error of only 2.36 m while requiring no real-world environment training.

Indoor Positioning Systems (IPSs) are designed to provide solutions for location-based services. Wireless local area network (WLAN)-based positioning systems are the most widespread around the globe and are commonly found to have a ready-to-use infrastructure composed mostly of access points (APs). They advertise useful information, such as the received signal strength (RSS), that is processed by adequate location algorithms, which are not always capable of achieving the desired localization error only by themselves. In this sense, this paper proposes a new method to improve the accuracy of IPSs by optimizing the arrangement of APs over the environment using an enhanced probability-based algorithm. From the assumption that a log-distance path loss model can reasonably describe, on average, the distribution of RSS throughout the environment, we build a simulation framework to analyze the impact, on the accuracy, of the main factors that constitute the positioning algorithm, such as t...

Indoor Positioning Systems (IPSs) are used to estimate the position of mobile devices in indoor environments. Fingerprinting is the most used technique because of its higher accuracy. However, this technique requires a labor-intensive training phase that measures the Received Signal Strength Indicator (RSSI) at all Reference Points (RPs) locations. On the other hand, model-based IPSs use signal propagation models to estimate distances from RSSI. Thus, they do not require expensive training but result in higher positioning errors. In this work, we propose SynTra-IPS (Synthetic Training Indoor Positioning System), a hybrid approach between a fingerprint and a model-based IPS that uses synthetic, simulated datasets combined with data fusion techniques to eliminate the fingerprint collection cost. In our solution, we use the map of the scenario, with known anchor nodes' positions and the log-distance signal propagation model, to generate several synthetic, model-based, fingerprint training datasets. In the online phase of our solution, the positions estimated by the several synthetic datasets using K-Nearest Neighbors (KNN) are combined using data fusion techniques into a single, more accurate position. We evaluated the performance of our SynTra solution in a real-world, large-scale environment using mobile devices with Bluetooth Low Energy (BLE) technology, and we compared our solution to classic approaches from the literature. Our results show that SynTra can locate mobile devices with an average error of only 2.36 m while requiring no real-world environment training.

Air Pollution (AP) is one of the main threats to global health. Real-time dynamic mapping of pollution distribution is of a crucial importance to the AP reduction and management. Conventional air quality monitoring relies on expensive and cumbersome monitoring stations. Such stations are sparsely deployed over a region – typically one to a few per city. The extrapolation of the dynamic spatiotemporal data away from these stations might be inaccurate. In this paper, we present a participatory Vehicle Sensor Network (VSN) based on low-cost mobile nodes deployed on public (taxi) vehicles. The system enables continuous real-time data acquisition, transmission, and utilization. As compared to the conventional approaches, our system greatly improves sensing coverage. The proposed platform enables the acquisition of a large amount of georeferenced and time-stamped data. It provides real time pollution mapping and historical data view. The system’s operational stability and continuity are e...

The heavy traffic in growing cities hurts the environment, commuters, and economy. Predicting such difficulties early helps increase road network capacity and efficiency and reduce congestion. Many academicians and transportation engineers ignore traffic congestion prediction despite its importance. Insufficient computationally efficient traffic forecast systems and high-quality city-wide traffic data contribute to this. Provide useful information to reduce traffic and construct shorter, more energy-efficient routes. Data storage increases traditional traffic forecasting training, storage costs, and delay. Smarter algorithms can handle today's city expectations because sensors can now communicate with their environment. A vibrant economy requires decent roads. Improving transportation requires uninterrupted highway traffic. To overcome these issues, smart city roadway traffic flow must be monitored in real time using enhanced internet of things (IoT) capabilities. Training data may contain sensitive information, raising privacy problems. This work addresses these issues by training the prediction model near data sources using federated learning (FL). The suggested strategy was tested using Mumbai, Chennai, and Bangalore traffic data. We compared the proposed method to centralized strategies to assess its efficacy. Our experiments confirm the model's traffic jam prediction accuracy. Our approach outperforms auto-encoder and convolutional neural network (CNN) in computer efficiency and prediction.

This report describes the design and implementation of an interface subsystem for a fall detection system using a pressure based floor sensor. The goal of the fall detection system is to detect and alarm when an elderly person has fallen. The subsystem covers communication between hardware and software, using the WiFi protocol MQTT. The communication is fast enough so that it does not limit other subsystem performance and allows for high expandability to accommodate the hardware's modular design. The interface module receives a probability of fall occurrence from the separate processing module, from which an average is taken over a 30 second time window to avoid false positives. Alarming is done through the use of text-to-speech voice API to make automated phone calls that retrieve user input to confirm or deny that help is on the way. A habit tracker proof of concept is provided that could improve the accuracy of fall detection by checking if the client is showing anomalies during a given day. A user interface is implemented using the Kivy environment. This environment has its own language which allows for separation of functionality and layout, which keeps the interface elements separate and leads to ease of use. Overall, this results in a strong alternative for fall detection that could be used to improve the time an elderly person can live at home safely without the need to move to a nursing home. We would like to thank our project proposer and supervisor prof. dr. Paddy J. French for the help and freedom within the project. We are very grateful for ir. Kianoush and dr. ir. Gerard J. M. Janssen because of their valuable feedback and support during the project. Many thanks go out to the Python community for providing documentation for many packages used in the project. Also, we would like to thanks our fellow project members I. Cornelis, S. Falkena, B. den Oude and H.J. Kruisse for their excellent work within the project, healthy discussions and overall great teamwork.

The Internet of Things (IoT) has revolutionized the way we live and work. the use of IoT technology setting provide numerous benefits educational institutions. One of the key advantages of using IoT is the ability to gather real-time data from a variety of sensors. In this paper we present a smart system for development and safety educational institutions using ESP32 board and Arduino sensors for temperature, humidity, fire, smoke and light, detecting fires and detecting cracks in the walls that may lead to the collapse of the institution using a camera. The aim of the study is to provide an effective automated system that enhances the quality of the organization's work, reduces time and energy, and increases accuracy and security. The hardware and software components of the system were described in detail, and experiments were conducted to evaluate the performance of the system. The results showed that the developed smart institution system provided accurate and reliable measurements of various parameters, and that the camera-based fire detection system was able to detect and alert users of any potential fire incidents and to detect cracks in the walls that might lead to the collapse of the institution to make measures necessary. The paper concludes with a discussion of the implications of the findings for future research and practical applications.

This paper presents an IoT based load forecasting and management system for distribution grids using Raspberry Pi. The proposed system integrates with real time data acquisition, statistical forecasting, and intelligent load management to enhance grid reliability. IoT enabled sensors are employed to capture real time electrical parameters, which are processed by Raspberry Pi and transmitted to the cloud for monitoring and control. The forecasting methodology incorporates statistical and time-series models, including Linear Regression, Multiple Regression, Polynomial Regression, ARIMA means Auto regressive Integrated Moving Average, SARIMA means Seasonal ARIMA, and Holt Winters, implemented in MATLAB Simulink. Two categories of features, based on historical demand patterns and calendar effects, are used to train the forecasting models. Furthermore, the influence of model selection on forecasting accuracy and scalability is analysed. Finally, an intelligent load management strategy is proposed to reduce peak demand stress, maximize operational efficiency, and provide a cost effective solution for distribution networks. The developed system shows improved accuracy, adaptability, and scalability, making it suitable for real time smart grid applications.

Owing to the enhanced flexibility in deployment and decreasing costs of manufacturing, the demand for unmanned aerial vehicles (UAVs) is expected to soar in the upcoming years. In this paper, we explore a UAV aided search and rescue (SAR) operation in indoor environments, where the GPS signals might not be reliable. We consider a SAR scenario where the UAV tries to locate a victim trapped in an indoor environment by sensing the RF signals emitted from a smart device owned by the victim. To locate the victim as fast as possible, we leverage tools from reinforcement learning (RL). Received signal strength (RSS) at the UAV depends on the distance from the source, indoor shadowing and fading parameters, and antenna radiation pattern of the receiver mounted on the UAV. To make our analysis more realistic, we model two indoor scenarios with different dimensions using a commercial ray tracing software. Then, the corresponding RSS values at each possible discrete UAV location are extracted and used in a Q-learning framework. Unlike the traditional location-based navigation approach that exploits GPS coordinates, our method uses the RSS to define the states and rewards of the RL algorithm. We compare the performance of the proposed method where directional and omnidirectional antennas are used. The results reveal that the use of directional antennas provides faster convergence rates than the omnidirectional antennas.

Frequent network-wide monitoring of the condition of roadways and railways prevent fatalities, injuries, and financial losses. Even so, agencies cannot afford to inspect vast transportation networks using present methods. Therefore, the idea of using low-cost sensors aboard connected vehicles became appealing. However, low-cost sensors introduce new challenges to improve poor signal quality which causes detection errors. Common approaches apply computationally complex filters to individual signal streams, which limits further improvements. This paper presents a method that combines signals from each traversal in a manner that leads to ever-increasing signal quality. The proposed method addresses the challenges of poor accuracy and precision of position estimates from global positioning system (GPS) receivers, and errors from the non-uniform sampling of low-cost accelerometers. The result is improved signal quality from a 20% improvement in signal alignment over GPS and a 90-fold enhancement in distance precision.

This paper examines the optimal placement of nodes for a Wireless Sensor Network (WSN) designed to monitor a critical facility in a hostile region. The sensors are dropped from an aircraft, and they must be connected (directly or via hops) to a High Energy Communication Node (HECN), which serves as a relay from the ground to a satellite or a highaltitude aircraft. The sensors are assumed to have fixed communication and sensing ranges. The facility is modeled as circular and served by two roads. This simple model is used to benchmark the performance of the optimizer (a Multi-Objective Genetic Algorithm, or MOGA) in creating WSN designs that provide clear assessments of movements in and out of the facility, while minimizing both the likelihood of sensors being discovered and the number of sensors to be dropped. The algorithm is also tested on two other scenarios; in the first one the WSN must detect movements in and out of a circular area, and in the second one it must cover uniformly a square region. The MOGA is shown again to perform well on those scenarios, which shows its flexibility and possible application to more complex mission scenarios with multiple and diverse targets of observation.

This paper describes a wireless real-time monitoring system (MS-BWME) to monitor the running state of pumps equipment in brine well mining and prevent potential failures that may produce unexpected interruptions with severe consequences. MS-BWME consists of two units: the ZigBee Wireless Sensors Network (WSN) unit and the real-time remote monitoring unit. MS-BWME was implemented and tested in sampled brine wells mining in Qinghai Province and four kinds of indicators were selected to evaluate the performance of the MS-BWME, i.e., sensor calibration, the system's real-time data reception, Received Signal Strength Indicator (RSSI) and sensor node lifetime. The results show that MS-BWME can accurately judge the running state of the pump equipment by acquiring and transmitting the real-time voltage and electric current data of the equipment from the spot and provide real-time decision support aid to help workers overhaul the equipment in a timely manner and resolve failures that might produce unexpected production down-time. The MS-BWME can also be extended to a wide range of equipment monitoring applications.

This paper describes a wireless real-time monitoring system (MS-BWME) to monitor the running state of pumps equipment in brine well mining and prevent potential failures that may produce unexpected interruptions with severe consequences. MS-BWME consists of two units: the ZigBee Wireless Sensors Network (WSN) unit and the real-time remote monitoring unit. MS-BWME was implemented and tested in sampled brine wells mining in Qinghai Province and four kinds of indicators were selected to evaluate the performance of the MS-BWME, i.e., sensor calibration, the system's real-time data reception, Received Signal Strength Indicator (RSSI) and sensor node lifetime. The results show that MS-BWME can accurately judge the running state of the pump equipment by acquiring and transmitting the real-time voltage and electric current data of the equipment from the spot and provide real-time decision support aid to help workers overhaul the equipment in a timely manner and resolve failures that might produce unexpected production down-time. The MS-BWME can also be extended to a wide range of equipment monitoring applications.

Within the Surveillance function in the A-SMGCS frame, Multilateration (MLAT) systems are being more and more used for location and identification of aircraft and of cooperating vehicles [1] on the airport surface. This situation, with increasing traffic in the downlink SSR channel, may lead to a too high number of superimposed, i.e. garbled, signals. The aim of this work is the need for reliable, simple effective algorithms to separate overlapped SSR signals. We proposed earlier some solutions [2,3], as well others can be found in the literature [5,6]. All of them require an array antenna at the receiver stations, while today's receiver stations are equipped with only one omni-directional antenna. In this paper, the sources separation algorithm based on array processing (PA: Projection Algorithm) is adapted to a single-antenna configuration, where the variation of carrier frequencies of different vehicular transponders [8] is exploited. Simulations with signals synthesized from real measurements give results that demonstrate the effectiveness of the algorithm in a frequency agility environment.

Transformers have reshaped sequence modelling, yet their value for embedded electronic-nose (e-nose) systems remains largely anecdotal. We present a systematic evaluation of ConvTran, a lightweight self-attention network originally proposed for generic time-series analysis, in the specific context of portable gas sensing. Two open datasets acquired with an eight-sensor Bosch BME688 board underpin the study: CoffeePow-4 (3583 traces across three coffee powders plus ambient air) and the imbalanced Aroma-7 extension that adds three fragranced creams for a total of 4750 traces. ConvTran is benchmarked against five deep-learning baselines (FCN, ResNet, InceptionTime, LSTM-FCN, ALSTM-FCN) and the proprietary Bosch AI-Studio classifier using accuracy, macro-F1 and macro false-positive rate, complemented by on-device memory and latency profiling. On CoffeePow-4, ConvTran attains 96.42% macro-F1 with 1.71 ms inference time while occupying 115 kB of flash. On Aroma-7, it preserves 96.03% macro-F1 at 2 ms and 557 kB, remaining faster than ResNet or InceptionTime, whose accuracy drops by 1.3%. Fully convolutional networks accuracy exceed ConvTran by 0.6% on the four-class task but loses 17% when the number of classes increases, highlighting the advantage of global self-attention for chemically similar odors. These findings demonstrate that an off-the-shelf transformer can satisfy the requirements of embedded devices, delivering state-of-the-art accuracy across balanced and imbalanced odor sets.

Deploying Internet of Things (IoT) on low-power lossy wireless sensor/actuator networks (LLN) in harsh industrial environments presents challenges such as dynamic link qualities due to noise, signal attenuations and spurious interferences. However, the critical demand for industrial applications is reliability of data delivery on low-cost low-power sensor/actuator devices. To address these issues, this paper proposes a fully autonomous scheduling approach, called Auto-Sched, which ensures reliability of data delivery for both downlink and uplink traffic scheduling and enhances network robustness against node/link failures. To ensure reliability, Auto-Sched assigns retransmission time slots based on the reliability constraints of the communication link. To avoid collision issues, Auto-Sched creates an upward pipeline-like communication schedule for uplink end-to-end data delivery, and a downward pipeline-like communication schedule for downlink scheduling. For enhancing network robus...

Wireless Sensor Networks (WSN) are often deployed to sample the desired environmental attributes and deliver the acquired samples to the sink for processing, analysis or simulations as per the application needs. Many applications stipulate high granularity and data accuracy that results in high data volumes. Sensor nodes are battery powered and sending the requested large amount of data rapidly depletes their energy. Fortunately, the environmental attributes (e.g., temperature, pressure) often exhibit spatial and temporal correlations. Moreover, a large class of applications such as scientific measurement and forensics tolerate high latencies for sensor data collection. Accordingly, we develop a fully distributed adaptive technique for spatial and temporal innetwork data compression with accuracy guarantees. We exploit the spatio-temporal correlation of sensor readings while benefiting from possible data delivery latency tolerance to further minimize the amount of data to be transported to the sink. Using real data, we demonstrate that our proposed scheme can provide significant communication/energy savings without sacrificing the accuracy of collected data. In our simulations, we achieved data compression of up to 95% on the raw data requiring around 5% of the original data to be transported to the sink.

Traffic congestion is a persistent problem in many metropolises worldwide. Despite the existence of traffic control systems, they are not always efficient enough to manage the ever-changing traffic density environment. The traditional approach of allocating specific times to each lane with the green light, regardless of the traffic situation, has not been very effective. In fact, it often can make the traffic congestion worse. Thus, the need for a more sophisticated system has emerged to simulate and optimize traffic control. This paper proposes the use of computer vision technology to develop a traffic control system that is based on periodic still photo feeds and compares different object detection models to find the best model for vehicle detection in our system . The system aims to enhance traffic flow by dynamically adjusting the traffic light cycles based on real-time traffic conditions.

Pothole detection remains a challenging task on the road, especially at low light conditions and may even current vision based systems experience degradation in performance. Here, we introduce a new pothole detection system that combines various deep models such as different versions of YOLO network. The main contribution of our method is the creation of an augmented night vision dataset via CycleGAN that closes the illumination gap between daytime and night-time images. This augmented dataset allows the detection system to perform accurately under low-light environments where traditional approaches generally struggle. Our work makes important contributions in the following ways: (i) Generation of augmented night vision dataset by CycleGAN, (ii) Comparative analysis of the models and (iii) it uses a new Bayesian fusion technique for decision combination. The work fills crucial gaps in adaptive dataset construction, model generalization, and decision fusion and provides an implementable solution to round-the-clock pothole detection.

Traffic signs are among the most important traffic equipment that are used in urban and non-urban areas and their purpose is to increase road volume and reduce delays while ensuring safe movement. Over the years, due to the growing trend of car production and car use, which has increased urban and road traffic, traffic signs have increased and become more diverse and efficient. One of these traffic control methods at intersections is the use of traffic signal scheduling techniques, which despite the advantages of this method has a major drawback, and that is that due to the dynamic behavior of traffic, this method has issues in predicting traffic signal timing especially in times of peak traffic. Designing appropriate green times for traffic signal lights with Adaptive Neuro-Fuzzy Inference System (ANFIS) technique in traffic signal controller is a feasible solution to tackle this issue in urban network congestion during peak hours. The capability to learn from experience is one of ...

We propose a fixed-lag smoother-based sensor fusion architecture to leverage the complementary benefits of rangebased sensors and visual-inertial odometry (VIO) for localization. We use two fixed-lag smoothers (FLS) to decouple accurate state estimation and high-rate pose generation for closed-loop control. The first FLS combines ultrawideband (UWB)-based range measurements and VIO to estimate the robot trajectory and any systematic biases that affect the range measurements in cluttered environments. The second FLS estimates smooth corrections to VIO to generate pose estimates at a high rate for online control. The proposed method is lightweight and can run on a computationally constrained micro-aerial vehicle (MAV). We validate our approach through closed-loop flight tests involving dynamic trajectories in multiple real-world cluttered indoor environments. Our method achieves decimeter-to-subdecimeter-level positioning accuracy using off-the-shelf sensors and decimeter-level tracking accuracy with minimally-tuned open-source controllers.

Intelligent Transportation Systems (ITS) increasingly leverage both visual and acoustic sensors to enhance traffic monitoring and management. Visual sensors, primarily cameras, provide high-resolution data for tasks such as vehicle detection, classification, speed estimation, and incident detection. Acoustic sensors offer complementary capabilities by capturing sound-based information, including engine noise, tire friction, and emergency sirens, facilitating applications such as vehicle counting, vehicle type recognition, emergency vehicle detection, and congestion monitoring through ambient noise analysis. This paper presents a comprehensive review of recent advancements (2021-2024) in the deployment and application of visual and acoustic sensing technologies in ITS. It evaluates sensor hardware, signal processing techniques, artificial intelligence (AI) applications, and performance metrics reported in over 30 peerreviewed studies. A comparative analysis of visual and acoustic approaches is provided, highlighting their respective strengths, limitations, and synergistic potential. Notable developments include the use of deep neural networks for multimodal data analysis, the emergence of large-scale benchmark datasets, and real-world pilot programs implementing audiovisual sensor fusion. The findings indicate that integrated visual-acoustic systems offer superior coverage, robustness, and accuracy, contributing to the development of safer, smarter, and more efficient transportation infrastructures.

In recent years, IoT platforms have become increasingly used due to their untapped potential. This paper aims to create an IoT system to monitor temperature and humidity in an enclosure The Raspberry Pi 4 SBC (Single-Board Computer) development board and ThingSpeak cloud platform will be used to make this system. Data from the DHT11 humidity and temperature sensor will be collected by the Raspberry PI 4 SBC development board, which will transmit it via the WiFi connection to the IoT ThingSpeak platform cloud for further analysis. The IoT ThingSpeak platform provides data storage, processing and visualization services.

In this article an experimental system of sensor network for monitoring physical variables applied to green technology in conjunction with internet of things (IoT) is presented. This, in a controlled ambient, that can guarantee the development and growth of the plants (exemplary/specimen). This application is focused on agriculture. Using Wireless Sensor Network (WSN) has a promising future due to current technical advances and its almost unlimited applications. This work propose WSN topologies, the measurement methodology, the sensors distribution and the visualization of the registered data in function of the area monitored, the communication protocol established by  Wi-Fi and the reads of the environmental temperature (ET), environmental humidity (EH) and ground humidity (GH) are registered and displayed in the web, during the registry of this measurements the data is analyzed and processed to perform relevant actions oriented to the control of physical variables at the monitore...

Very high throughput satellites (VHTS) are the new trend in satellite communications systems in order to satisfy the increasing demand for both higher throughput and ubiquitous connectivity. Implementing an IP interactive network over a VHTS would enable the satellite to compete with terrestrial networks by offering ubiquitous added value services for end-user traffic. Even so, the simulations presented in this paper show that a 30% of throughput can be lost due to co-channel interferences. In existing interactive satellite networks such as REDSAT or AmerHis, the return uplink transmissions are inherently benefited from the MF-TDMA scheduling to mitigate the co-channel interferences present in VHTS. In such networks dynamic resource assignation (DAMA) is executed at each SuperFrame period (<100 ms). Therefore, any feasible optimization on the scheduling shall be performed in real time. In this paper, two parallel problems are faced at the same time: co-channel interference mitigation and real time scheduling. In particular, two novel interference-aware scheduling algorithms for a DVB-RCS2 return uplink are presented. Despite other previous works, the proposed algorithms are designed on the basis to be executed in real time on a fixed SuperFrame period basis. The performance assessment of the proposed algorithms is carried out through system-level simulations based on realistic satellite scenarios and interactive traffic models using DAMA in real time.

In this paper, we report on extensive experiments conducted to evaluate Internet of Things (IoT) sensor performance in monitoring urban air quality. As certified sensors showed a considerably reduced air quality measurement error of 4.3% compared to uncalibrated sensors at 8.5%, our results highlight the crucial function of sensor calibration. The performance of sensors was impacted by environmental factors; higher temperatures produced better accuracy (3.6%), while high humidity levels caused sensors to react more quickly (2.3 seconds). The average air quality index (AQI) recorded by inside sensors was 45, but outside sensors reported an AQI of 60. This indicates that the positioning of the sensors had a substantial influence on the air quality data. Additionally, the methods of data transmission were examined, and it was found that Wi-Fi-transmitting sensors had lower latency (0.6 seconds) and data loss (1.8%) than cellulartransmitting sensors. These results emphasize the significance of environmental factors, sensor placement strategy, sensor calibration, and suitable data transmission techniques in maximizing IoT sensor performance for urban air quality monitoring, ultimately leading to more accurate and dependable air quality assessment.

The term &quot;Real-Time Operating System (RTOS)&quot; refers to systems wherein the time component is critical. For example, one or more of a computer&#39;s peripheral devices send a signal, and the computer must respond appropriately within a specified period of time. Examples include: the monitoring system in a hospital care unit, the autopilot in the aircraft, and the safety control system in the nuclear reactor. Scheduling is a method that ensures that jobs are performed at certain times. In the real-time systems, accuracy does not only rely on the outcomes of calculation, and also on the time it takes to provide the results. It must be completed within the specified time frame. The scheduling strategy is crucial in any real-time system, which is required to prevent overlapping execution in the system. The paper review classifies several previews works on many characteristics. Also, strategies utilized for scheduling in real time are examined and their features compared.

21 Abstract—Early detection of the fire which produces a rapid action is essential in any firefighting system. A suggested smart system based on Internet of things is presented. Arduino Mega 2560 with the flame sensors is the core of the proposed system to detect the fire. The entire city is monitored remotely via the Internet by the smart center of firefighting, which is distributed in various locations. DeviceBit and Blynk platforms have been used for monitoring and sending notification immediately with the fire location to the smart center of firefighting. The proposed system is designed and implemented to be flexible, efficient with low cost to be practical and applicable.

The basic reproductive number (R 0 ) and superspreading potential (k) are key epidemiological parameters that inform our understanding of a disease's transmission. Often these values are estimated using the data obtained from contact tracing studies. Here we performed a simulation study to understand how incomplete data due to preferential contact tracing impacted the accuracy and inferences about the transmission of SARS-CoV-2. Our results indicate that as the number of positive contacts traced decreases, our estimates of R 0 tend to decrease and our estimates of ktend to increase. Notably, when there are large amounts of positive contacts missed in the tracing process, we can conclude that there is no indication of superspreading even if we know there is. The results of this study highlight the need for a uni ed public health response to transmissible diseases.

This study presents the design, development, and evaluation of an AI-powered GPS-based robotic lawn mower featuring autonomous navigation and control using a Raspberry Pi platform. The system integrates RTK-GNSS for centimeter-level localization, AI-driven path planning (A*, Theta*, DWB/TEB), and multi-sensor obstacle detection using LiDAR, ultrasonic sensors, and computer vision. Field experiments were conducted on outdoor lawns (12-20 m × 8-15 m) with slopes up to 5°, encompassing open grass, moderate, and dense obstacle conditions. Performance metrics included navigation accuracy, coverage efficiency, overlap percentage, obstacle detection precision and recall, obstacle handling latency, path tracking error, throughput, energy consumption, and blade RPM stability. Results demonstrated superior performance, with navigation accuracy of 0.025 m, coverage efficiency of 98.6%, and overlap of only 6.4%, exceeding target benchmarks. Obstacle detection precision (96.8%) and recall (94.5%) ensured reliable identification of static and dynamic hazards, while handling latency averaged 225 ms, enabling timely collision avoidance. Path tracking error remained at 0.042 m, supporting stable operation, and throughput reached 8.3 m²/min. Energy consumption was low at 3.8 Wh/m², with a battery runtime of 162 minutes, surpassing the 150-minute target. Blade RPM stability of 1.8% maintained consistent cutting performance. Comparative analysis showed that the proposed system outperformed commercial robotic mowers and manual push mowers in accuracy, efficiency, safety, and sustainability. The integration of AI algorithms, RTK-GPS localization, and sensor fusion significantly improved operational adaptability, efficiency, and safety. The mower's modular architecture, electric operation, and optimized coverage contribute to reduced environmental impact and labor requirements. These findings demonstrate the potential of low-cost, AI-enabled autonomous systems to transform residential and commercial lawn maintenance. Future work may explore scalability, predictive maintenance, and grass health monitoring to expand functionality and market applicability.

In today's expanding cities, pipeline networks are becoming an essential part of the industrial infrastructure. Monitoring these pipelines autonomously is becoming increasingly important. Inspecting pipelines for cracks is one specific task that poses a huge burden on humans. Undetected cracks may pose multi-dimensional risks. In this paper, we introduce the Pipeline Leak Identification Emergency Robot Swarm (PLIERS) system, an industrial system that deploys Internet-of-Things (IoT), robotics, and neural network technologies to detect cracks in emptied water and sewage pipelines. In PLIERS, a swarm of robots inspect emptied pipelines from the inside to detect cracks, collect images of them, and register their locations. When the images are taken, they are fed into a cloud-based module for analysis by a convolutional neural network (CNN). The CNN is used to detect cracks and identify their severity. Through extensive training and testing, the CNN model performance showed promising scores for accuracy (between 80% and 90%), recall (at least 95%), precision (at least 95%), and F1 (at least 96%). Additionally, through the careful design of a prototype for a water/sewage pipeline structure with several types of cracks, the robots used managed to exchange information among themselves and convey crack images to the cloud-based server for further analysis. PLIERS is a system that deploys modern technologies to detect and recognize cracks in pipeline grids. It adds to the efforts of improving instrumentation and measurement approaches by using robots, sensory, IoT principles, and the efficient analysis of CNNs.

As cities continue to expand, there has been a substantial increase in demand for factories and sewage systems, which in turn necessitated the need for maintaining the pipeline systems involved. These are typically difficult, dangerous, and expensive to investigate manually by humans, and therefore the use of automated robots is crucial to identifying cracks. Therefore, we propose PLIERS (Pipeline Leak Identification Emergency Robot Swarm). PLIERS is a system consisting of a swarm of robots that are used to investigate pipes for any cracks while communicating with one another as well as a server system. The robots are mounted with cameras to collect images of these cracks, which are then analyzed using a machine learning algorithm by the server to detect and confirm the cracks and their severity.

Interference and spoofing of Global Navigation Satellite Systems (GNSS) represent growing operational and security concerns. This paper describes a reproducible workflow for GNSS forensic monitoring that relies on low-cost, commercially available equipment: an RTL-SDR V4 receiver for passive I/Q collection and an SA6 handheld spectrum analyzer for spectral observation. RF captures were combined with Android raw GNSS measurements obtained via the GnssLogger application, supplemented by inertial sensor traces, to extract reliable forensic indicators. Case studies and synthetic performance plots are presented to illustrate how anomalies can be identified and interpreted. All active experiments were carried out under controlled conditions using cable-injection and shielded setups to ensure nonradiating compliance II.

Outdoor parking systems are one of the most crucial needs in a smart city to find vacant parking spaces in outdoor environments, such as roadsides, university campuses, and so on. In a typical outdoor parking system, the detection of a vehicle entering and leaving the parking zone is a major step. At present, there are numerous external sensor-based and camera-based parking systems available to detect the entrance and leaving of vehicles. Camera-based parking systems rely on sophisticated camera set-ups, while sensor-based parking systems require the installation of sensors at the parking spots or vehicles’ sides. Due to such complication, the deployment and maintenance costs of the existing parking systems are very high. Furthermore, the need for additional hardware and network capacity increases the cost and complexity, which makes it difficult to use for large deployment. This paper proposes an approach for outdoor parking utilizing only smartphone integrated sensors that do not ...

Secara tradisional, pendeteksian kualitas air dilakukan secara manual yaitu dengan cara sampel air diperoleh secara insitu dan dikirim untuk dianalisis ke laboratorium yang memakan waktu proses, biaya dan sumber daya manusia yang cukup lama. Teknik tersebut tidak menyediakan data secara real-time. Oleh sebab itu, perlu adanya inovasi dan teknologi baru yang memudahkan dalam pemantauan dan analisis data kualitas air secara real-time dengan pendekatan mikrokontroler dan sensor parameter kualitas air tertentu, dimana data yang sudah terekam akan terkirim melalui nirkabel dengan pendekatan Internet of Things (IoT). Nilai parameter seperti suhu, kelembaban udara, ketinggian muka air, kekeruhan dan pH air secara umum dapat direkam secara baik oleh masing-masing sensor. Tujuan penelitian ini adalah membuat alat ukur parameter perairan seperti nilai pH, kekeruhan air, ketinggian air, suhu dan kelembaban udara sekitar berbasis web Thingspeak melalui webserver maupun telegram. Metode yang digunakan pada penelitian ini adalah perancangan sistem, pemrograman mikrokontroler Arduino Mega berbasis ATmega2560 dan NodeMCU berbasis ESP8266 melalui Arduino IDE, perakitan serta pengujian alat baik skala prototype maupun secara langsung di lapangan. Berdasarkan hasil pengujian alat di lapangan menunjukkan bahwa sensor suhu air mampu merekam nilai yang fluktuatif mulai dari 32,4 -34,1 o C. Sedangkan sensor kelembaban udara mencatat kisaran 33,5 -35,6%. Untuk mengetahui tinggi muka air sungai, maka sensor ultrasonic mencatat cukup baik dengan nilai 28 -71 cm. pH air direkam oleh sensor pH dengan data rekaman dalam bentuk tegangan air mulai 3,34 -5,38 Volt. Hasil rekaman sensor tersebut kemudian dikirim secara online berbasis IoT dan diterima melalui aplikasi telegram.

Non-intrusive load monitoring (NILM) systems have gained immense popularity in the last two decades. Although many solutions were developed using the NILM approach, the majority of solutions failed to identify low-power-consuming appliances. However, a NILM system deployed in a domestic installation should be capable of identifying low-power-consuming appliances precisely. Therefore, we propose two real-time NILM solutions that can identify low-power residential appliances. These two solutions rely on active power and harmonic information extracted from the measured current waveform. We analyzed the performances of the two solutions using simulations and real-world experiments. Results indicate that both solutions can correctly identify appliances with an average accuracy above 90 percent.

Smart manufacturing environments (digitalized production systems with integrated sensor networks and data analytics capabilities) require advanced predictive maintenance capabilities, yet implementation faces significant barriers due to data privacy concerns and proprietary knowledge protection requirements. Traditional machine learning approaches necessitate centralized data repositories, creating obstacles for collaborative maintenance optimization across organizational boundaries. This research develops and evaluates a federated learning framework that enables effective predictive maintenance while preserving data privacy in manufacturing networks. The study implemented a horizontal federated learning architecture with secure aggregation protocols and differential privacy techniques across multiple aerospace manufacturing facilities. System performance was evaluated through comparative analysis against centralized and standalone approaches across multiple predictive maintenance use cases. The federated approach achieved 93.7% of centralized model accuracy while eliminating cross-facility data sharing, with failure prediction lead times approaching centralized performance while substantially outperforming standalone models. Computational overhead increased modestly, but network data transfer requirements decreased by 94%. Privacy analysis confirmed that proprietary process parameters could not be reconstructed from shared model updates. This research advances smart manufacturing capabilities by providing a practical implementation framework for privacy-preserving predictive maintenance across organizational boundaries, enabling industry collaboration while maintaining intellectual property protection.

Meteorological observation systems are extremely data-driven. However, several factors affect measurements, which require the use of environmental metrology techniques to increase the quality of measurements, decrease errors and evaluate measurements uncertainty. In this paper, we propose and develop a framework that integrates, process and visualizes sensor data and its associated metadata (for rainfall monitoring). This task is accomplished with a workflow designed to correct raw sensor data, which uses an elastic stack based infrastructure to collect, transform, and store sensor data and metadata. We validated our framework using real precipitation data from a Tipping Bucket Rain Gauge.

Industries need solutions that can automatically monitor oil leakage from deployed underwater pipelines and to rapidly report any damage. The location prediction of mineral reservoirs like oil, gas, or metals in deep water is a challenge during the extraction of these resources. Moreover, the problem of ores and mineral deposits on the seafloor comes into play. The abovementioned challenges necessitate for the deployment of underwater wireless sensor networks (UWSNs). Anchor-based localization techniques are segregated into range-free and range-based processes. Range-based schemes depend on various techniques like angle of arrival (AoA), time of arrival (ToA), time difference of arrival (TDoA), and received signal strength indicator (RSSI). In this article, the localization of these leakages is performed by using range-based metrics for calculating the distance among anchor nodes (ANs) and target nodes (TNs). This estimated distance is further optimized to minimize the estimation error. A multilateralism procedure is used to estimate the optimal position of each TN. The results exhibit that the proposed algorithm shows a high performance when compared to previous works, in terms of minimum energy consumption, lower packet loss, rapid location estimation, and lowest localization error. The benefit of using the proposed methodology greatly impacts on identifying the leakage area in mobility-assisted UWSN, where rapid reporting helps to lower the loss of resources. Les industries ont besoin de solutions permettant de surveiller automatiquement les fuites de pétrole des pipelines sous-marins déployés et de signaler rapidement tout dommage. La prédiction de l'emplacement des réservoirs de minéraux comme le pétrole, le gaz ou les métaux en eaux profondes est un défi lors de l'extraction de ces ressources. En outre, le problème des minerais et des dépôts minéraux sur le fond marin entre en jeu. Les défis mentionnés ci-dessus nécessitent le déploiement de réseaux de capteurs sans fil sous-marins (UWSN). Les techniques de localisation basées sur l'ancrage sont classées en deux catégories : les procédés sans portée et les procédés basés sur la portée. Les procédés basés sur la portée dépendent de diverses techniques comme l'angle d'arrivée (AoA), le temps d'arrivée (ToA), la différence de temps d'arrivée (TDoA) et l'indicateur de la force du signal reçu (RSSI). Dans cet article, la localisation de ces fuites est effectuée en utilisant des métriques basées sur la distance pour calculer la distance entre les noeuds d'ancrage (AN) et les noeuds cibles (TN). Cette distance estimée est ensuite optimisée pour minimiser l'erreur d'estimation. Une procédure multilatéralisme est utilisée pour estimer la position optimale de chaque TN. Les résultats montrent que l'algorithme proposé est très performant par rapport aux travaux précédents, en termes de consommation d'énergie minimale, de perte de paquets réduits, d'estimation rapide de la position et d'erreur de localisation minimale. L'avantage de l'utilisation de la méthodologie proposée a un impact important sur l'identification de la zone de fuite dans les UWSN á mobilité assistée, où un signalement rapide permet de réduire la perte de ressources.