In recent years, the use of solar technology as an alternative to conventional methods of electricity generation has increased. However, they have low conversion efficiency; one way to increase energy production is by using Solar Tracking Systems (STS), which cause energy expenditure. Monitoring systems are required to calculate the energy balance between produced and consumed. In this research, the design and implementation from a concurrent approach of an embedded system for energy monitoring in solar applications is presented, obtaining a low energy consumption, high connectivity, scalable, modular, and open architecture system. Experimental tests were carried out considering five proposed energy-saving strategies. These tests recorded the energy consumption of actuators, electronic hardware, and generated power, resulting in a 16.47% increase in the energy budget and a reduction in the global power consumption of 7.27%. Notably, the developed embedded system exhibited a low energy consumption of 0.326Wh.

Air pollution is a critical contributor to the global climate change crisis and poses severe threats to human health worldwide. In this context, this paper introduces an innovative multi-sensor air quality monitoring (AQM) device designed to address the critical challenge of atmospheric pollution in urban environments. The AQM device features an optimized geometry specifically suited for mobility. It enables precise air quality (AQ) monitoring by measuring concentrations of NO2, O3, and CO, along with particulate matter (PM) across three size categories: PM1, PM2.5, and PM10. The AQM device ensures reliable operation across temperature variations from 10°C to 40°C and humidity levels ranging from 10% to 70%. Outdoor experiments were conducted in the city of Marseille to validate the efficiency of the AQM device and assess its ability to provide street-level air quality data. The AQM device was validated by comparing its measurements with data from four reference instruments (i.e., government-operated fixed stations) located within an 8 km radius of the center of Marseille. Real-time data is made available through a dedicated software server platform, offering geo-localized air quality information and detailed reports. The developed device offers excellent autonomy, with a full battery discharge lasting up to 28 hours, allowing it to be used throughout an entire day without the need for recharging. The proposed multi-sensor device was developed in the scope of the SMILE project (Self-calibrating air pollution Multi-sensors and ICDT platform to Leverage citizen’s Empowerment). The project aims to empower end users with the responsibility of carrying, activating, and monitoring their own sensor devices while utilizing specialized apps on their mobile phones.

Latin American agriculture encounters significant challenges such as inefficient land use and vulnerability to climate change, with smallholder farmers being particularly affected. This paper proposes a modular based system that integrates embedded systems, environmental sensors, for real-time monitoring and adaptive control. The system utilizes a Raspberry Pico coupled with advanced sensors measuring temperature, humidity, potential of hydrogen (pH), liquid level, light intensity, air quality, and electrical current. Actuators regulate nutrient delivery in response to pH levels, while intelligent lighting systems enhance plant growth conditions. Remote monitoring facilitated by a vision-equipped camera system allows the detection of anomalies and the tracking of plant growth. Experimental results demonstrated temperature stability of ±1∘C, humidity variation within ±5%, 92% accuracy in anomaly detection, and response times of less than 10 seconds.

This paper presents a design of an experimental electric measurement and control system for a custom hydrogen PEM (Proton-Exchange Membrane) fuel cell stack. The article briefly describes the operating principle of closed cathode PEM hydrogen fuel cells. Then a simple balance of plant for controlling a unique fuel cell stack developed by our project partner, the HUN-REN Institute of Materials and Environmental Chemistry, Renewable Energy Research Group, with special membranes will be introduced. The paper briefly presents the sensors and actuators selected for this setup, as well as the hardware and software of the control electronics. The article concludes by presenting the results of measurements taken in the test environment. After presenting these results, we discuss those parts of the project that build on the results of these experimental measurements and have promising research potential.

This study introduces a novel single-hole, dual-core suspended fiber optic sensor that integrates the surface plasmon resonance (SPR) effect and the Mach-Zehnder interference (MZI) principle, enabling the simultaneous monitoring of both salinity and temperature in seawater. The sensor comprises of two segments of multimode fiber (MMF) and a segment of single-hole dual-core suspended fiber (SHTSCF), where the surface-sputtered gold film (Au) on the SHTSCF segment excites the SPR effect for salinity detection; while the MMF and SHTSCF segments together form an MZ interference structure for temperature detection, effectively solving the crosstalk problem between salinity and temperature measurements. The experimental findings reveal that the sensor exhibits a salinity sensitivity of 0.5186 nm/‰ within the salinity bracket of 5‰ –40‰, and a temperature sensitivity of 0.1263 nm/°C across the temperature spectrum of 5°C– 50 ∘ C. The maximum temperature and salinity fluctuations caused by the sensor under different temperature and salinity conditions are 3.2 ∘ C and 1.38 ‰ , respectively, indicating that it has good stability. Moreover, a crosstalk effect of −0.149 nm/°C is observed between temperature and salinity measurements. This SPR sensor demonstrates excellent stability, repeatability, and reliability, with a compact structure, providing a new technological pathway for the synchronous monitoring of dual parameters in seawater.

In recent years, real-time monitoring of pollutants in flue gas emissions from industrial and transportation sectors has gained significant attention due to rising environmental concerns and the implementation of pollutant capture technologies. Despite these advancements, existing systems often fail to accurately measure pollutant concentrations in high-temperature flue gases with sufficient temporal resolution. To overcome these limitations, we present a compact and power-efficient flue gas monitoring system capable of simultaneously tracking 15 vital air quality parameters, including CO2, O2, particulate matter (PM1.0, PM2.5, PM4.0, and PM10), temperature, humidity, volatile organic compound (VOC) index, CH4, CO, NO, NO2, SO2, and H2S, with reliable spatial and temporal resolutions. Central to the system is a modular precooling unit, which reduces flue gas temperatures from approximately 150 ∘ C to within 30 ∘ C– 45 ∘ C, enabling sensors to function optimally under thermal stress. To validate the robustness and discrimination capability of the system, field experiments were conducted by monitoring emissions from coal and torrefied biomass combustion in an industrial-scale boiler. The results demonstrate that average CO2 emission from coal combustion reaches approximately 618 ppm, which is 1.43× higher than those observed from biomass. Additionally, the power analysis of the system reveals an average current consumption of 0.0385 A, which can support the continuous operation for nearly six days using a 5000-mAh battery. The proposed system offers a scalable, cost-effective alternative to bulky commercial analyzers, with strong potential for deployment in industrial emission monitoring, environmental sensing, and smart infrastructure applications.

Approximately one-third of a human’s lifetime is spent sleeping, and sleeping posture plays a pivotal role in both sleep quality and overall health. Therefore, there is a pressing need for an affordable, yet high-performance sleeping posture recognition system with adaptive adjustment capabilities. In this study, we present a sleeping posture recognition system based on a controller, utilizing an airbag mattress integrated with sensors. The system positions airbags at five key body regions to form a mattress and transmits the real-time data to a PC via an air pressure sensors module. Furthermore, the system employs a closed-loop control mechanism to optimize support distribution via real-time pressure monitoring and local air pressure adaptation, thereby enhancing sleep quality.

Observations of air pollution have become an increasing concern for authorities and citizens due to emissions from population growth and urbanization. In this regard, low-cost wireless sensor networks (LWSNs) have emerged as a popular, cost-effective solution for monitoring and estimation of air-pollutant levels in local areas. Due to environmental vulnerability, ensuring the required performance and reliability of these sensing devices remains an open problem. This article presents the development of a dependable Dempster-Shafer inference (DDSI) framework based on evidence theory for colocated low-cost sensors for air quality monitoring. This approach facilitates fault detection and accounts for uncertainty to enhance the performance of the sensor network. A switching mechanism is employed in the inference layer to select the most reliable information based on the probability of the current operational status of sensors, thereby leveraging the resilience and data integrity of the monitoring system. The proposed method is comprehensively validated in both laboratory and real-world settings. The DDSI framework is then tested in monitoring humidity, temperature, and particulate matters (PMs) in the suburbs. The results are benchmarked with data collected from state-run air quality monitoring stations (AQMSs). Statistical analysis is conducted to show the accuracy of the proposed framework and a high alignment with station observations, achieving an R2 of up to 0.918 for meteorological parameters and 0.892 for fine particles (PM2.5).

This article proposes a multimodal fusion framework to address the challenges of detecting and tracking specialized vehicles and dynamic targets in complex industrial park environments. The framework integrates LiDAR, , and an inertial navigation system (INS) to achieve precise obstacle perception and stable tracking through dynamic region of interest (ROI) cropping, optimized point cloud clustering, target detection, and multimodal perception fusion. First, a path-aware dynamic ROI cropping method and a multiregion density-aware seed point cloud ground segmentation approach are introduced to improve adaptability and point cloud processing efficiency. Second, a two-stage refinement strategy method is proposed to enhance target clustering accuracy. Furthermore, by combining the 2-D detection network, a multimodal perception fusion module, and a multiobject tracking (MOT) strategy, the framework significantly improves fusion efficiency and matching accuracy. Field tests demonstrate that the framework achieves excellent performance, with static object localization deviations below 0.8 m and reliable state estimation for dynamic targets. On a custom dataset, the monocular Camera achieves 91.67% accuracy for specialized vehicles, while the fusion framework exhibits strong adaptability and reliability in complex scenarios

Efficient speed planning is crucial for the safe and comfortable navigation of autonomous vehicles in dynamic environments. This paper introduces a novel energy-efficient, jerk-controlled speed planning approach based on quintic polynomial generation. We present a systematic methodology to determine the dynamic speed of autonomous vehicles by integrating several factors, including the relative velocity with dynamic obstacles, the curvature of the base frame and optimal selected path, road adherence, and road gradient. The direct integration of road adherence and gradient into the speed profiling approach contributes to improving vehicle safety. Comparative analysis with literature methods demonstrates the significant impact of jerk smoothness on energy efficiency. Simulations are conducted in a joint simulation between Simulink and SCANeR Studio vehicle dynamics simulator, followed by validation on a real-world dataset. Our findings elucidate the significance of the proposed planning method in enhancing safety, energy economy, driving comfort, and computational efficiency, while effectively addressing a wide range of critical situations.

Glucose is a vital biomarker involved in numerous physiological and pathological processes, making its detection a key factor in diabetes monitoring. To enhance convenience, real-time tracking, comfort, and accuracy, glucose measurement techniques are rapidly advancing towards smartphone integrated wearable, non-invasive, and low power systems. In this work, a diabetes monitoring system is developed which can be used as a wearable health tracker. The device offers dual ways of monitoring glucose levels in diabetic patients; first by glucose measurement via blood using a screen-printed electrode sensor (SPES), second by volatile organic compounds (VOCs) measurement via breath analysis using an ethanol sensor. Additionally, an oximetry sensor is included in the system to monitor important human vitals such as heart rate, similar to commercial health trackers. The system is fabricated on a printed circuit board and its size is 3 cm ×3 cm which is suitable as a wearable device. It also consumes low power and has capabilities of wired/wireless charging and wired/wireless communication. Furthermore, customized Windows and Android applications have been developed to visualize the obtained data in user’s computer or smartphone. The conducted experiments aimed at validating the performance of each sensors have yielded promising results. These findings indicate that the developed system has significant potential to be utilized as a point-of-care testing device for real-time diabetes monitoring.

The coffee industry has experienced significant expansion in recent years, driven by increasing demand for high-quality coffee. The quality of coffee beans is conventionally evaluated using extraction procedures that emphasize sensory characteristics such as crema, body, and heart. This paper proposes a novel approach to evaluate coffee beans quality by utilizing gas sensors to measure the degassing process of coffee beans. The proposed technique provides the classification coffee beans quality without extraction process. The example of coffee beans in our experiment includes three distinct groups of coffee beans: (1) freshly roasted beans, (2) roasted beans that allowed resting within an optimal degassing period, and (3) roasted beans that had been roasted for over one month. Our experimental results demonstrate that the gas release profile during degassing successfully differentiated the quality of the beans across the various groups. Each batch of coffee beans has distinct gas release patterns that indicate their quality, whether poor or high. These results confirm that the measuring degassing behavior of coffee beans can evaluate the coffee beans quality. Moreover, the proposed approach has the potential to improve quality of control in coffee production, streamlining the assessment process without the need for traditional extraction methods.

The real-time vehicle health monitoring system presented in this study is intended to discover and detect automobile actuator and sensor issues. To assess the bike's health, the system keeps an eye on internal variables including gasoline level, engine temperature, and carbon monoxide (CO) levels. The primary objective is to develop an embedded system that can provide reliable information about the vehicle's condition, enabling timely maintenance and reducing the risk of accidents. The system is capable of detecting faults with minimal latency, even in the presence of disturbances and uncertainties. The proposed system enhances vehicle safety, reliability, and performance by providing predictive maintenance alerts and optimizing vehicle performance parameters.

Temperature and humidity chambers are often employed for stress testing materials. In the case of cultural heritage materials, it is also crucial to incorporate light condition in these evaluations. Consequently, controlling these parameters is essential to effectively simulate accelerated environmental conditions. This letter outlines the design and implementation of an embedded system that manages temperature, humidity, and light levels. Built on an ARM Cortex-M3 System on Chip, the system integrates various temperature and humidity sensors and actuators, along with a light controller. It also features an embedded user interface and facilitates communication with an external PC. The validity of our proposal is demonstrated through the implementation of a proportional-integer control mechanism for the regulation of temperature and relative humidity.

The study introduces a loosely coupled, highly reliable, all-scene and embedded autonomous braking system (ABS) for autonomous electric Formula racing cars with four-wheel braking. The ABS incorporates the Emergency Braking System (EBS) for emergency braking and the Electronic Stability Control (ESC) system for dynamic braking. The research offers a comprehensive overview of the design concept of the ABS and the process of its simulation experiments and its real-vehicle validation tests. The system ensures the safety and stability of the car in the autonomous state (AS), which has been successfully applied to the Formula Student Autonomous China (FSAC) A01 racing car.

Autonomous vehicles (AVs) are heralding a new era in transportation systems, attracting extensive attention from both academia and industries. Presently, predominant efforts are directed toward enhancing safety and efficiency in AV operations. However, the crucial aspect of human discomfort, integral to the AV user experience and capable of influencing user acceptance and eventual AV deployment, remains relatively understudied. To bridge this gap, this paper delves into the influential factors of human discomfort in AVs through human-in-the-loop studies utilizing a high-fidelity autonomous driving simulator featuring six-degrees-of-freedom motions. The investigation examined the impacts of various significant factors, including AV maneuvers, driving styles, and road types, on human discomfort. Through the application of multivariate analysis of variance and mixed logit modeling techniques, the data was quantitatively analyzed. The findings revealed the relationship between various autonomous driving factors and human discomfort, furnishing invaluable insights for the design of future autonomous vehicles.

The rapid expansion of autonomous technologies, the rise of computer vision, and edge computing present exciting opportunities in healthcare monitoring systems. Fall prevention is especially important for the elderly because falls from this age group often result in fatalities and serious injuries. Fall detection devices that can quickly recognize falls and alert emergency services have become more and more popular as a result. The primary goal of the project is to increase elderly home safety by implementing an ambient intelligence-based automated emergency recognition system. We present a unique method for fall posture detection utilizing an intelligence surveillance camera and a class of efficient models called MobileNets for mobile and embedded vision applications. A real-time embedded solution persuaded from “edge AI” is implemented using the state-of-the-art Object detection: single shot detector (SSD) Mobile Net V2 and Internet of things embedded GPU platform NVIDIA’s Jetson Nano.

With the rapid advancement of industrialization and urbanization, the adverse effects of air pollution on human health and environmental protection have become increasingly significant. This study developed an air quality monitoring device equipped with various air detection sensors and integrated with a Wi-Fi sensor for data collection and cloud upload. A multilayer long short-term memory (LSTM) model was used to analyze the data, and strategies for deployment on edge computing devices were explored. The study also leveraged the high performance and low power consumption of embedded chips to process air quality data locally in real time. Experimental results showed that the system achieved 91.6% accuracy. In terms of precision and accuracy, our model improved by 8.3% and 10.6%, respectively, compared to traditional multilayer perceptron (MLP) and by 9.7% and 11.3%, respectively, compared to recurrent neural network (RNN), significantly enhancing the efficiency and reliability of air quality classification. Moreover, this research not only provides new perspectives for environmental monitoring and data processing but also elucidates the application of edge computing in intelligent environmental monitoring, which is crucial for promoting low-carbon development.

This paper focuses on an embedded system for air quality control and hazardous gas detection using multiple sensors to trigger real-time danger alerts. The system employs and integrates gas sensors MQ-2, MQ-7, and MQ-135, temperature, and humidity sensors for assessing many combustible gases including methane, carbon monoxide alcohol smoke and even fire. These sensors send signals to an embedded microcontroller which controls air and environmental quality for the circumferential range. Apart from the gas sensors, a fire sensor has been integrated within the system, improving its efficiency in ascertaining cases of fire outbreak in the presence of gas leakages. In addition to this, Power BI works with the system for sensor monitoring and data visualization through the sensors being connected online. The dashboard shows the most important parameters such as the level of gas leakage and the type of gas involved, the temperature of the surroundings, and the humidity. Power BI supports how to visualize what is going on at that time to monitor environmental conditions, how bad is the gas leakage, and make quick decisions. The dashboard also helps in looking out for risks by showing past trends of data and carrying out market predictions. The integration of multi-sensor systems with a drone is intensified to outstretch the boundaries even further where remote monitoring of industrial sites, areas that have been hit by disasters, and even of cities, is possible. The drone equipped with the embedded system provides the real time gas leak detection temperature, humidity monitoring and fire threat assessment in environments where the human presence is quite dangerous. This system is also easy, cheap and provides an admirable solution for environmental monitoring on a day to day basis for the sake of public safety, reduction in the response rates to dangerous situations and the encouragement of smart city designs. The research in this study focused on both stationary and mobile wirelessly enabled embedded systems for real time data acquisition and their application in drones for environmental monitoring and risk management using low cost and real time systems.

This paper proposes the development of a system to evaluate the performance of defense against spoof fingerprint attacks on access control devices equipped with fingerprint recognition technology. To enhance the security of fingerprint recognition-based access control systems, it is essential to defend against spoof fingerprint access attacks. This paper aims to improve the security of access control systems by proposing a performance evaluation system for spoof fingerprint attacks. For the performance evaluation of the proposed system, the process involved the creation of spoof fingerprints, the development of a performance evaluation jig for access control devices, and the design of a performance evaluation system. Additionally, performance evaluation scenarios and test items were defined for spoof fingerprint recognition. The results of simulations using access control devices with embedded spoof fingerprint defense technology were visualized and report of the results was confirmed.

A significant proportion of mobile surveying systems in the market are not economically viable due to their inconvenience in operation such as large size, complex data processing requirements and limited accessibility to areas without vehicle access. This paper proposes a model to deploy a rover-based system to address the challenges to measure the height of the building and object in urban environments using a low-cost, easy-to-assemble system comprising ultrasonic sensors, stepper motors and a laser system. Here, it integrates calibration mechanisms to be highly accurate, and the rover's modular architecture promotes robustness and easy replication for multiple scenarios. This advances the measurement of building heights in urban settings by enhancing users’ control of the process, and in delivering results that reflect local requirements.

The Temperature monitoring procedure relies on an Microcontroller to perform accurate real-time temperature monitoring operations. It is paired with a temperature sensor which operates as a low-cost solution for different environments. The device shows real-time temperature data on an OLED screen that delivers easily read able critical temperature readings through high-contrast display while consuming minimal power. This paper proposes a system which allows users to set custom temperature threshold levels that automatically activate warning alerts when measurements reach those preselected values to boost security applications. A Bluetooth module was integrated into the system to enable smartphone-based data transmission which allows users to monitor temperatures from their mobile phones through an application. This paper demonstrates how controller based systems handle real-time temperature monitoring by providing dependable affordable solutions for temperature monitoring control and remote function control.

This paper presents innovative approach to home safety combines advanced sensor technology with smart automation to create a robust defense against potential disasters. The system uses a mix of software and hardware components to improve inhabitants' safety and security by delivering timely detection and pertinent alerts. These sensors continuously monitor environmental conditions and seismic activity, providing real-time data to the system. Additionally, a buzzer is incorporated to provide audible alerts, while a servo motor may be employed for physical actions such as closing windows or doors in response to detected threats the system is programmed using the Arduino IDE and embedded C language, allowing for flexibility and customization based on specific user requirements. This paper outlines the installation of a complete safety system intended to identify and address fire and earthquake emergencies in a home environment.

The efficient utilization of high value and mobile/portable medical equipment is a key towards improving hospital’s operations and costs. In this study, a real time energy monitoring and location tracking system for medical equipment is developed and deployed in Thammasat University hospital in Pathumthani province. An embedded device in form of a smart plug is prototyped with a current sensor, Bluetooth Low Energy (BLE) wireless interface, WiFi wireless interface, and a microcontroller to monitor the energy usage of a medical equipment and to track its location, simultaneously. The smart plug is acting as an electronics tag which can be tracked within the service area of our previously developed real time location tracking system which consists of a group of location tracking devices called anchors and a location server on a public cloud computing system. The energy usage data for each medical equipment is estimated and reported to the server. The staffs of the medical equipment department of the hospital can locate any equipment and monitor its energy usage status remotely over the internet. Energy utilization and movement records can be used for later data analysis.

This study explores IoT-based forest nursery monitoring using Sony Picam 2 and Raspberry Pi B2 (8 GB RAM). The primary objective revolves around the measurement and continuous monitoring of plant leaf color, a crucial indicator of plant health and nutrient status. To accomplish this, a Python program has been developed to systematically monitor and analyze variations in plant leaf color within the same species, and even within individual plants. Additionally, the study extends its focus to nutrient deficiencies, encompassing essential elements like N, P, K, and 13 micro-nutrients, shedding light on the critical aspect of plant nutrition in nursery settings. To further enrich our comprehension of forest sapling growth, a growth model incorporating techniques has been meticulously designed. The development and refinement of this model were greatly facilitated by Google CoLab. The next phase of the research will involve thorough field testing of the developed model at a nursery in Bhubaneswar. This testing will include a variety of plant species. The primary objectives are to evaluate its accuracy and effectiveness in real-world scenarios and to explore its scalability for application in larger fields. This interdisciplinary study seamlessly bridges the realms of technology, biology, and agriculture, culminating in the creation of a robust system for efficient forest nursery management and early detection of plant health issues. By doing so, this research contributes significantly to the sustainable growth and conservation of forest ecosystems, ensuring their long-term vitality and resilience.

Waste is causing a serious environmental problem. Waste management and circular economy offers a best alternative for preserving the environment and protecting nature resources. This paper presents an based system for waste identification and sorting, particularly focusing on plastic, which is the less decomposed waste, using computer vision techniques. The data, used for system validation, comprises publicly available datasets and a locally collected dataset, devoted to plastic classification and detection. Performance metrics demonstrate that YOLOv8 outperforms other deep learning solutions, in real-time waste detection and is well suited for implementation on a Raspberry Pi 4 Model B. The system outperforms also existing methods in terms of efficiency, accuracy, and speed, and is a promising solution for addressing the global waste management challenge.

In this work, we propose the concept of the Smart Rail, an innovative system for the continuous monitoring of the track geometry based on embedded arrays of Fiber Bragg Grating sensors and Raman-based distributed temperature sensors. First, we discuss how our technology design, based on a custom metallic patch embedding the FBG sensors and brazed on the track, overcomes the robustness concerns of the State of the Art. The metrological principle is formulated based on an analytical/FE model allowing the correlation of the measured signals to the local curvature deformation of the rail, and then to reconstruct the global track geometry. The effect of spatial sampling on the detection of even short-wave defects is addressed through simulations, as being a crucial trade-off between effectiveness and complexity. Experimental results performed on a first prototype demonstrate an efficient strain transfer with excellent agreement with the theoretical predictions. Hence the proposed technology seems very promising for the next generation of monitoring systems, in terms of robustness and compatibility with maintenance operations.

Enhancing interactions with natural and user-friendly computer interfaces (HCIs) requires the use of hand gestures. This article illustrates a particularly created brilliant neural network that can identify the flat-based platform's movements. Real-time applications on low-power devices can benefit from the suggested approach, which is solely software-implemented and tailored for resource-constrained contexts. To classify hand gestures with high accuracy and minimal computing complexity, the network analyzes input from infrared (IR) sensors. Particular care is taken to reduce the model's memory and processing needs without sacrificing recognition efficiency. The system is tested using a variety of hand gestures and shows that, despite having little hardware resources, it is capable of quickly and accurately recognizing movements. The software solution offers a scalable method for integrating gesture detection systems into a range of HCI applications on wearable and embedded devices. The system demonstrated competitive performance and low power consumption following rigorous testing.

Attacks on the sensor-controller (S-C) channel, which enable the infusion of false data, present substantial risks to the security of autonomous vehicles. This paper endeavors to address the challenge of guaranteeing secure path-following control for autonomous vehicles under the threat of False Data Injection (FDI) attacks, which through the utilization of an event-triggered output feedback model predictive control approach. To ensure the controller receives uncompromised system states amidst FDI attacks, a distributed robust multivariate observer (DRMO) is employed, which can facilitate the estimation and differentiation of uncompromised system states and attack signal simultaneously. Building upon the uncompromised system states provided by the observer and considering various constraint conditions, a predictive controller is formulated to ensure secure control of autonomous vehicle path following. Additionally, an event-triggered mechanism is introduced, dynamically adjusting the controller update frequency, resulting in significant savings in computational and communication resources. Finally, showcase an example to substantiate the efficiency of the proposed scheme.

Autonomous Vehicles aim to understand their surrounding environment by detecting relevant objects in the scene, which can be performed using a combination of sensors. The accurate prediction of pedestrians is a particularly challenging task, since the existing algorithms have more difficulty detecting small objects. This work studies and addresses this often overlooked problem by proposing Multimodal PointPillars (M-PP), a fast and effective novel fusion architecture for 3D object detection. Inspired by both MVX-Net and PointPillars, image features from a 2D CNN-based feature map are fused with the 3D point cloud in an early fusion architecture. By changing the heavy 3D convolutions of MVX-Net to a set of convolutional layers in 2D space, along with combining LiDAR and image information at an early stage, M-PP considerably improves inference time over the baseline, running at 28.49 Hz. It achieves inference speeds suitable for real-world applications while keeping the high performance of multimodal approaches. Extensive experiments show that our proposed architecture outperforms both MVX-Net and PointPillars for the pedestrian class in the KITTI 3D object detection dataset, with 62.78% in APBEV (moderate difficulty), while also outperforming MVX-Net in the nuScenes dataset. Moreover, experiments were conducted to measure the detection performance based on object distance. The performance of M-PP surpassed other methods in pedestrian detection at any distance, particularly for faraway objects (more than 30 meters). Qualitative analysis shows that M-PP visibly outperformed MVX-Net for pedestrians and cyclists, while simultaneously making accurate predictions of cars.

Lower-limb amputations pose significant challenges, with over 150000 cases annually in U.S., leading to a high demand for effective prosthetics. However, only 43% of lower-limb prosthetic users report satisfaction, primarily due to issues with socket fit, which is critical for comfort, stability, and preventing injury. This study presents a novel and deployable sensing system for potentially real-time monitoring of prosthetic socket fit by using pressure sensors and convolutional neural networks (CNNs) to analyze the pressure distribution within the socket. Two CNN-based strategies were implemented, namely, a long-term time series analysis and a single time step representation. The system was designed for edge deployment on the Sony Spresense microcontroller, maintaining a small model size while achieving high accuracy. Results show that the CNN models, particularly those optimized with the stochastic gradient descent (SGD), demonstrated robustness and high transferability. This system provides a cost-effective, portable solution to improve prosthetic fit, enhancing patient care and preventing gait-related injuries.

The analysis of biological fluids, particularly exhaled breath (EB), offers a promising noninvasive approach for early disease diagnosis by detecting volatile organic compounds (VOCs). Traditional techniques like gas chromatography-mass spectrometry (GC-MS), while sensitive, are limited by high costs and complexity. This study explores the application of temperature modulation (TM) to enhance the performance of metal oxide semiconductor (MOS) sensors in identifying and quantifying VOCs in complex mixtures. Using a custom-built electronic nose (eNose) system equipped with four MOS gas sensors and a square-triangular TM pattern, mixtures of three VOCs, namely acetone, isopropanol, and toluene, were analyzed across three concentration ranges. Sensible parameters extracted from each sensor response were used to discriminate VOCs and concentrations by random forest (RF) classifier achieving an accuracy of 91%, precision of 91%, recall of 89%, and F1 -score of 89% in classifying the mixtures. Feature re-mapping coupled with a CatBoost classifier leveraging individual VOC analysis reduced the experimental burden and achieved an 84% classification accuracy. These findings demonstrate that TM combined with an address key challenges in complex gas mixture analysis, advancing the potential of portable eNose systems for clinical diagnostics.

This study addresses the issue of temperature-induced variations in the output data of miniature inertial measurement units (MIMUs) caused by material properties and manufacturing inconsistencies. To mitigate this problem, a temperature drift compensation method based on an improved gated recurrent unit (GRU) neural network is proposed. Specifically, a GRU-based temperature compensation model optimized using the black-winged kite algorithm (BKA) is introduced. To validate the effectiveness of the BKA-GRU model, simulation experiments were conducted using MIMU data across the full temperature range, and the compensation results were compared with those obtained from the GRU and optimized monarch butterfly algorithm-GRU (OMBA-GRU). Experimental results demonstrate that the BKA-GRU model achieves higher accuracy and greater stability compared with the other two temperature compensation models.

In this study, high-performance flexible wearable temperature sensors are developed based on innovative material system design combined with electro fluidic jet printing fabrication technology. In terms of core material innovation, the PEDOT:PSS/PANI/PDMS multi responsive thermo sensitive material system was constructed through a molecular-level synergistic composite strategy, and the synergistic effect between the conductive network, temperature response, and mechanical flexibility is far superior to that of the traditional single-component-sensitive materials. In addition, electro hydrodynamic jet printing (EHD printing) is only used as a precision manufacturing platform to realize the precise deposition of micro structured electrodes, and the microstructural integration of copper paste electrodes and composite-sensitive materials on 0.025 mm PET substrate, which is advantageous in precisely controlling the deposition morphology of functional materials. The optimized sensor shows breakthrough performance indexes: −0.867% °C−1 resistance temperature coefficient and 0.997 linearity over a wide range of 25– 80 ∘ C, 0.19 s ultra-fast response combined with 0.1 ∘ C high resolution, and the performance parameters are significantly better than those of similar flexible sensors. This study opens up a new path of flexible sensing through material system innovation, providing innovative solutions for smart electronic skin and precision medical monitoring.

Safety-critical scenarios for autonomous vehicle testing have been rare in the real world. However, virtual simulation technology can provide numerous and diverse testing scenarios. Various effective methods can be employed to generate unknown safety scenarios and determine dangerous scenarios for tested autonomous vehicles. To meet time-varying safety-critical scenario construction requirements for virtual testing of autonomous vehicles, this study proposes a data-model-driven method for generating the edge cases of high-risk lane-changing scenarios. The trajectory time generative adversarial network named the Traj-TimeGAN is proposed to generate emergency lane-changing trajectories based on data from HighD dataset. In addition, a safety distance-based constraint model is designed to define the safety boundary and generate the initial state of a tested autonomous vehicle. Further, a generalization generation method is developed to generate many risk-critical scenario edge cases, and a lane-changing scenario dataset is constructed. The proposed method is verified by experiments, and the average root-mean-square error for 520,000 generated emergency trajectories is 1.9×10−3, indicating a high similarity between generated and real trajectories. Based on the results, in 99.93% of the 520,000 generated risk-critical lane-changing edge cases, the absolute value of time to collision (TTC) between the tested automated vehicle and the lane-changing background vehicle is less than 1 s. Finally, the results show that the proposed method can effectively generate high-risk lane-changing edge cases for autonomous vehicle testing.

The objective of this paper is to eradicate the power theft without human interaction. Power theft is a major issue faced worldwide. Here we are introducing a new concept called endangering, to minimize the power theft in electrical power distribution. In this concept, if any malfunctioning occurs, then the power supply of all authenticated users are shut down by use of relays and in the meantime high voltage is passed over through the transmission line of that particular area, which will damage the equipment’s of the unauthorized power users. For a given region, the power theft is detected by continuously computing the difference between transformer’s output power and the power consumed by the authorised users. The receiver module is placed in the main power station to continuously monitor all authorized users power consumption pattern. In addition, it provides instant billing along with complain booking. The proposed power theft detection scheme ensures effective use of power by authorized personnel.

The Landslides are catastrophic natural events that position important hazards to social lives, structure, and the atmosphere. Early detection and monitoring of landslide- prone areas are essential to mitigate these risks. This paper presents a Landslide Finding and Observing System (LFOS) using Wireless Sensor Networks (WSNs) and the Zigbee communication protocol. The proposed system leverages a grid arrayed with sensor nodes of landslide- prone areas to monitor conservational factors such as earth moistness, earth heaviness, vibration, hotness, and tilt— key indicators of potential landslides. Each sensor node collects real-time data and wirelessly transmits it to a central Zigbee Coordinator, which aggregates the data for further analysis. The processed data is sent to a Base Station for real-time monitoring, where threshold-based alerts are generated in case of abnormal readings, and triggering timely notifications to relevant authorities. The system utilizes Zigbee's low-power, short-range mesh network to ensure reliable data transmission over large, remote areas, while minimizing energy consumption. Through the integration of sensor data and wireless communication, this system offers an efficient, cost- effective for landslide earlywarning and monitoring.

This Research proposes an efficient wireless monitoring system for brain stroke in patients through more reliable and low-power ZigBee protocol, based on different sensors that record several inputs related to brain strokes. In communication with patients care takers, doctors and hospital handling telemedicine and emergency support to patients with proper medical aid avoiding the overloads and increases the working efficacy of this model with Wireless Body Area Network. This study focuses on a comparative analysis of efficiency and measures based on cost-effectiveness of ZigBee with other communication protocol based on mesh network.

The temperature and humidity requirements for cellar wine was crucial for the quality and preservation of the wine. This paper designed a ZigBee based wine cellar environment monitoring system, which used wireless nodes to form a wireless network to achieve real-time monitoring of temperature and humidity inside the wine cellar. This system built an upper computer interface through LabVIEW software platform to realize the functions of wine cellar temperature and humidity data display, data storage, data analysis and abnormal alarm. Through remote monitoring and control, users could know the temperature and humidity in the wine cellar at any time, so that the wine cellar was in a suitable storage environment.

Fire presents a serious risk to life and can be triggered by various factors across different environments. In some areas, the absence of fire detection systems is often due to the high initial investment costs, particularly when the need for such systems is temporary. To tackle this issue, we propose a portable fire detection system as an innovative solution. This system features sensors that monitor for fire outbreaks and alert authorities. A key challenge to its adoption is the limitation on power consumption. To mitigate this, we have developed a custom microcontroller board designed for a low-power, battery-operated portable fire detection system, which has been field-tested. A thorough power analysis of the system has been conducted, revealing a sensor battery life of 62 days. This paper details the design features and presents the findings of the power analysis performed.

Whenever there is an arrival of an unfamiliar person in your house, this smart home security system will inform you automatically about the situation through the use of CCTV cameras, LiDAR technology and your mobile app. The system can even recognize unknown visitors who enter the home and report them to the user's mobile app for confirmation. If there is any abnormal behavior, the user can instantly call the authorities. The use of LiDAR technology provides clean detection even during adverse weather or smoke. Zigbee technology, the other part of the system, works intermittently with no power malfunction, providing continuous security surveillance.

Rapid expansion in the quantity and variety of solid and hazardous waste because of ongoing economic development, urbanization, and industrialization is posing a growing challenge for national and municipal governments to ensure efficient and long-term waste management. As reported by the Global trash Management Market Report 2007, the total amount of municipal solid trash produced globally in 2006 was anticipated to be 2.02 billion tons, a rise of 7% annually since 2003.To reduce the risk to patient and public health and safety, as well as environmental risk, waste management, transportation, and disposal must be carefully handled. Waste is best able to achieve its economic value when it is separated. There is currently no system in place for households to separate dry, moist, and metallic garbage. In order to send home waste directly for processing, this work suggests an Waste Segregator Robotic (WSR), which is an affordable, simple-to-use alternative. Its purpose is the process of separating the waste into dry and wet waste. Capacitive sensors are used by the WSR to differentiate between wet and dry trash, trash level detection, foul smell detection, relocation of the system and send alert to the person in-charge. Experimental findings demonstrate that the WSR has successfully integrated the separation of waste into moist and dry waste. Send an alert to the person in-charge for various issues such as trash level capacity, presence of foul smell and relocation of the system.

This paper presents the design of a sensor network capable of transmitting data over long distances (up to 1000 meters) achieving reliable data, with the aim of improving energy consumption efficiency in Bulding Energy Management Systems (BEMS). The processing system uses microcontroller, the communication protocol proposed is Zigbee and the IoT (Internet of Things) platform to remotely view and control sensor data is Ubidots. The main contribution of this project is the design of environmental sensor node with high range of communications capabilities using Zigbee devices and found the right combination of the different communication factors (distance, spreading factor, bandwidth, and power). The project seeks to contribute to the field of building automation and long-distance communications allowing greater efficiency in energy consumption, reducing costs and minimizing environmental impact. Finally, communication validation is planned.

Trains are well known as a reliable, affordable, and speedy means of transportation in metropolitan cities in India and around the globe. Though convenient and ever popular, train accidents in India are often blamed on human mistake. With the speed of trains high and the latency in human intervention, it is always a major task to prevent such crashes. This study suggests a proactive method of minimizing railway accidents by using Radio Frequency Identification (RFID) technology. The main goal of the suggested system is to forecast possible train collisions and notify the central control room or train drivers prior to an accident. There are few mechanisms in place to avoid train crashes at present, and thus the use of an advanced Anti-Collision Device (ACD) system is essential. The suggested train collision avoidance system combines RFID technology, Zigbee communication, machine learning, and artificial intelligence (AI) to improve railway safety. Every locomotive has an automated monitoring system, and the railway network is segmented into two-kilometer sections, each having a unique track number. RFID tags placed on the trains are scanned by onboard RFID scanners, and this information is processed by an AI system to check for the existence of other trains on the same path. When there is a possible collision, the system sends alarms to train controllers through Zigbee, and an automatic braking system is activated to halt the crash. This advanced system offers real-time collision detection and avoidance, vastly enhancing railway safety and minimizing the possibility of train collisions.

The paper highlights a Wireless Sensor Network (WSN) implementation for environmental monitoring, emphasizing cost-effectiveness and adaptability. APIs designed to handle values instead of voltage levels increase system resilience, while open standards promote security, cost efficiency, and auditability. The data shows a diurnal temperature range from 20°C (night) to 38°C (day), stable humidity at 38%, and UV radiation peaking at 6 (day) and dropping to 1.5 (night). Smoke levels are consistently high at 490 μg/m3, while toxic gas concentrations slightly rise to 0.5 ppm during the day from 0.45 ppm at night. Fire metrics remain low and stable. These findings highlight the need for UV protection, air quality controls, and consistent fire safety measures. The system achieves effective environmental monitoring while remaining adaptable for future needs, underscoring its value in scalable, cost-efficient, and sustainable public management solutions.

The Explosion Risk Detection System is a cutting-edge solution designed to mitigate the risk of explosions in hazardous environments. This advanced system integrates multiple sensors, including gas detectors, temperature, and pressure sensors, to detect potential explosion risks in real-time. By leveraging wireless sensor network technology with GSM and Zigbee capabilities, the system enables prompt alerts to nearby personnel and transmits critical data to management authorities, facilitating swift response and evacuation. The system's multi-sensor approach provides comprehensive monitoring of environmental conditions, allowing for early detection of potential explosion risks. Real-time data analysis and machine learning algorithms enable the system to identify patterns and anomalies, ensuring accurate and reliable risk assessments. With its advanced notification system, the Explosion Risk Detection System minimizes the risk of explosions, protecting lives and preventing damage to equipment and infrastructure. By providing a proactive and reliable explosion risk detection solution, this system significantly enhances safety and efficiency in industries prone to explosion hazards, such as oil and gas, chemical processing, and mining.

This requires ubiquitous sensor networks to monitor and instantaneously predict dangerous gas concentrations at ground level deployed within smart city environments. A sensor network is a collection of many distributed sensors that can be used together to gather data in real-time and from standard logs across an environment, generally allowing users to see, hear, or feel whether emissions are entering their air as they happen. Cities attaching these sensor networks can provide real-time air quality data for municipalities and citizens taking control of our health. It can analyze pollution hotspots, detect trends and patterns over time, and act as an early warning system for dangers. Such work creates a framework for interventions to be undertaken quickly and efficiently to reduce air pollution as soon as possible and work towards protecting residents' public health. Sensor networks can also provide historical data, which is necessary for tracking long-term trends and assessing how effective pollution control measures have been. Furthermore, this information can validate city-specific policies and exercise recommendations for reducing air pollution in smart cities. It will give decision-makers and citizens the data they must act on while making well-informed decisions for cleaner air in their cities.

Falls are one of the major causes of injury for elderly and mobility-impaired patients, which require immediate detection and intervention to avoid severe repercussions. The proposed project is a Patient Fall Monitoring System based on Arduino and Bluetooth technology for real-time fall detection and immediate caregiver notification. The system employs a MEMS sensor for continuous monitoring of patient movement by analyzing posture changes, speed, and acceleration for detecting sudden and uncontrolled falls. A threshold-based fall detection algorithm is implemented to analyze sensor data to differentiate between normal activity and true falls. Once a fall is detected, the system instantaneously sends notifications over Bluetooth to enrolled mobile devices and triggers a buzzer alarm for local alerting. Experiments showed high sensitivity to detect different types of fall events including slipping, stumbling, and sudden loss of balance. Regardless of environmental factors such as vibrations and the range constraints of Bluetooth, the system was found to be reliable in conveying emergency messages without perceivable delay. The open-source design of CONTROLLER allows for continuous improvement, with future expansions potentially being Wi-Fi or cellular communication for increased coverage. The system improves patient safety through real-time monitoring, quick alerts, and real-time intervention.

This research introduces an innovative wearable gesture- to-speech translator that improves nonverbal communication while also incorporating smart environmental controls. The system interprets hand motions using a sensor-equipped glove, which is subsequently transformed to text and synthesized into speech for real-time interaction. A liquid-crystal display delivers sensory input, while a speech module and amplifiers produce crisp audio. Despite connectivity, the gadget includes an environmental surveillance system that measures warmth via a DHTll sensor. When the temperature rises above a certain level, a CPU fan turns itself on in order to cool the system. The gadget also supports Bluetooth-controlled illumination functioning along with gesture-based alerts via text through a GSM module for offsite notices. The combined application of adaptive transmission and automated functionality improves accessibility and usability, resulting in a full, versatile wearable solution for those with speech difficulties.

This study offers a strategy that uses GSM technology to assist consumers in effectively managing their electricity usage. Users may turn off devices or check their solution's SMS-based remote control and monitoring capabilities. Additionally, the gadget records energy consumption over time, giving customers insights into areas where they can reduce their energy and financial expenditures. The integration of GSM technology ensures the system's accessibility and usefulness. Ultimately, this approach reduces energy waste in residential and commercial environments, encourages energy conservation, and lowers electricity expenses.

The increasing demand for efficient energy management has led to the development of prepaid energy meters. This project presents a GSM-based prepaid energy meter that enables users to monitor and control electricity consumption remotely. The system consists of an microcontroller, LDR sensor, GSM module, and an OLED display to keep track of energy usage and balance deduction. Users can recharge their meters via SMS, and the system will automatically disconnect power when the balance reaches zero. This innovation ensures transparency in billing and prevents unauthorized electricity usage.

Theft of two-wheelers is a persistent issue, and thus, effective security systems need to be developed to reduce losses. This paper presents a novel anti-theft device that uses a vibration sensor to enhance the security of two-wheelers. The system detects unauthorized movements or tampering through a highly sensitive vibration sensor integrated with a microcontroller. In case the system identifies some abnormal vibrations, it sets up an alarm to warn the owner, and it is capable of setting up notification over wireless communication technologies. This solution has proved to be cheaper, energy-efficient, and reliable to protect two-wheelers in a better manner without reducing the comfortability of users. Complete testing has proved the accuracy of this system for theft attempts and its possible practicality.

In this study, a GSM-based wireless sensor network architecture is proposed to support precision agriculture through remote monitoring and control of vital environmental parameters. The work establishes real-time data acquisition and analysis to identify the growing significance of data-driven farming in contemporary agriculture. The network employs sensors to monitor temperature, humidity, soil moisture, , and water levels and send this data through GSM modules to a central server. A strong backend system, developed with Python frameworks such as Flask or Django, processes the sensor data and converts it into actionable information for farmers. The system allows bidirectional communication, enabling farmers to control agricultural environments through mobile apps or web-based dashboards remotely. Real-time sensor readings are displayed on mobile phones, with SMS alerts and notifications activated when parameters stray from set thresholds. The frontend interface, which is built using Android, JavaScript, and the Kivy framework, provides an easy-to-use interface for remote monitoring and control, allowing for quick responses to environmental fluctuations. The system makes a contribution to precision agriculture through the provision of an integrated solution for remote monitoring and control of critical agricultural parameters. With the combination of sensor data acquisition, GSM voice/data capabilities, and user-friendly interfaces, the system facilitates farmers to maximize resource use, sustain soil health, and enhance crop management as a whole. This method seeks to reduce resource wastage and maximize farm productivity.

This paper presents the design and implementation of an RFID-GSM based intelligent cart system to automate the retail checkout process and reduce long queues and manual billing inefficiencies. The proposed system is built around an microcontroller, integrated with an EM18 RFID reader for automatic product identification via RFID tags. An I2C OLED displays item details and running totals in real-time, while a push button allows customers to finalize their shopping. Upon checkout, the total bill is calculated and sent via SMS using a SIM900A GSM module to the customer's registered mobile number, enabling a paperless transaction. A buzzer provides audible feedback during item scans. The proposed system is powered by a regulated supply, programmed using Arduino IDE, and interfaced via USB. The investigated system reduces billing time, minimizes human errors, supports eco-friendly operations, and enhances the shopping experience through seamless automation.

This paper proposes a GSM-based children's rescue system designed for earthquake emergencies, emphasizing cost-effectiveness and simplicity while ensuring rapid child rescue. The system operates in three key stages: data acquisition, classification, and alert notification. Sensors collect temperature, and heart rate data, which are then digitized and classified to assess the child's condition. If abnormal values are detected, an alert notification is sent via GSM to parents and rescue teams, providing real-time location data through GPS. The hardware implementation, based on Raspberry Pico, converts analog sensor signals into digital data for processing. The system's efficacy is validated through various scenarios, demonstrating its ability to detect critical conditions and promptly trigger alerts, enhancing child safety during disasters.

“Sober Lock: Smart Bike Security System with Alcohol Detection and GPS Tracking” is an emerging technology that addresses drunk driving as a big global challenge, contributing to many fatalities per year. Existing bike lock systems lack mechanisms to prevent intoxicated riders, which, in turn, may create unsafe road conditions. This system is designed for the detection of alcohol consumption, prevention of ignition, and real-time GPS tracking. It consists of the microcontroller that interconnects several components, including an I2C LCD, a GPS tracking module (NEO-6M), and an alcohol sensor (MQ-3). For the system to stop the occurrence of accidents due to alcohol consumption, the alcohol sensor will enable the bike to be unlocked only if the rider is considered sober. Thus, to unlock the system, the smartphone application built from MIT App Inventor interacts with the GPS module in providing real-time updates of the bike's location, thus allowing consumers to monitor their bikes remotely and subsequently prevent theft or ease recovery in case of loss. The I2C OLED acts feedback-wise, giving real-time updates about its location and alcohol detection to interact with the user easily. Similarly, the system's real-time GPS tracking module helps users track the bike via an online web interface. Experimental results prove its accuracy for alcohol detection and GPS tracking, making it a good solution to avert drunk-driving scenarios and vehicle security.

This paper presents the design of an advanced assistive stick for visually impaired individuals, integrating ultrasonic sensors, GPS tracking, and GSM communication to enhance mobility. Traditional walking sticks have limitations in detecting obstacles, which can hinder independent navigation. The proposed solution improves upon conventional designs with ultrasonic sensors for faster and more accurate obstacle detection, reducing accident risks. GPS tracking provides real-time location data, aiding navigation in unfamiliar areas, while GSM technology enables emergency alerts and location sharing with caregivers. Additionally, the device includes a feature to help users locate the stick if misplaced. By enhancing safety, independence, and inclusivity, this smart navigation tool supports equitable opportunities and improved well-being. It contributes to sustainable development goals and aims to enhance the autonomy and quality of life for individuals with visual impairments.

The study establishes smart glasses embedded with AI voice assistance that covers obstacle detection and object detection, OCR (Optical Character Recognition), and GPS tracking for visually impaired individuals. The smart glasses improve mobility and independence by providing real- time obstacle and object detection. The audio-guided navigation in the glasses helps the users overcome different environments, whether indoor, public transport, or city streets. These glasses use the internal sensors to scan the surroundings for possible hazards and inform the user to take action when navigating. GPS tracking allows monitoring a location, enhancing safety. The AI voice assistance makes the interaction intuitive and easy, and OCR detects text in images, allowing the reader to read signs or documents through audio feedback. This innovative technology enables visually impaired persons to traverse new and difficult settings with minimal assistance, promoting confidence and autonomy. The great deal of new input methods integrated into wearable technology pushes the assistive technology field forward in terms of greatly enhancing the quality of life for users that are visually impaired. With the integration of AI voice assistance, GPS tracking, Optical Character Recognition, Object detection, and Obstacle detection, Smart Glasses provide real-time navigation to improve accessibility and promote independence for the users.