Sensor Equipment Research Articles

An Extensive Analysis of Machine Learning Applications in HVAC

Heating, ventilation and air-conditioning (HVAC) accounts for around 40% of the total building energy con¬sumption. It has therefore become a major target for reductions, in terms of both energy usage and CO2 emissions. In the light of progress in building intelligence and energy technologies, traditional methods for HVAC optimi¬zation, control, and fault diagnosis will struggle to meet essential requirements such as energy efficiency, occu¬pancy comfort and reliable fault detection. Machine learning and data science have great potential in this regard, particularly with developments in information technology and sensor equipment, providing access to large vol¬umes of high-quality data. There remains, however, a number of challenges before machine learning can gain widespread adoption in industry. This review summarizes the recent literature on machine learning for HVAC system optimization, control and fault detection. Unlike other reviews, we provide a comprehensive coverage of the applications, including the factors considered. A brief overview of machine learning and its applications to HVAC is provided, after which we critically appraise the recent literature on control, optimization and fault diagnosis and detection. Finally, we provide a comprehensive discussion on the limitations of current research and suggest future research directions.

RELAKA: Robust ECC based Privacy Preserving Lightweight Authenticated Key Agreement protocol for healthcare applications

With the advancement of cutting-edge technologies, the Internet of Medical Things (IoMT) has assisted the healthcare sector by facilitating interaction between healthcare service providers and patients in remote areas. In IoMT, wearable or implantable sensors collect the patient’s record and share the information through a public network. Health-related information about the patient must be protected from a variety of attacks by the adversary since it is sensitive and extremely vulnerable to attacks. The sensor equipment that is implanted in the patient is also resource-constrained and has a low power capacity. The entities involved in the communication must be authenticated with one another in order to protect patients’ health information, anonymity, and reliability. While several authenticated key agreement protocols have been proposed, many suffer from high computational costs and storage cost, making them unsuitable for lightweight applications. This paper proposes a secure three-factor robust Elliptic Curve Cryptography (ECC) based mutually authenticated and key agreement protocol known as RELAKA for the IoMT environment, utilizing the benefits of one-way hash function. In proposed scheme, all entities, including the healthcare service providers and wearable sensors, are authenticated by the medical server. Subsequently, a secret key is established for each communication session and shared between all the entities. Additionally, mechanism for appropriate user revocation and re-registration is integrated to provide additional security in cases where a user’s QR code is tampered with by the attacker. The privacy of the proposed protocol is investigated by the potential use of zero knowledge proof. Furthermore, the efficacy of the authentication is examined by challenge and response mechanism. The informal security analysis demonstrates its resistance to threats such as DoS, impersonation, message modification, password guessing, and so on. The performance evaluation of RELAKA protocol indicates that the execution, communication, and storage costs is reduced by 87.59%, 43% and 60.71% respectively. Moreover, the outcomes of the AVISPA simulation illustrate that the RELAKA successfully evades both active and passive attacks. In addition, real-world testbed environment is developed with Raspberry pi 4 model B and the experimental results verifies the robustness of the proposed protocol. According to theoretical analysis and experimental evaluation, the RELAKA scheme is more secure and efficient than the existing protocols.

Fault detection and treatment method of power converter station based on man-machine cooperative intelligence

Abstract Aiming at the problems of low efficiency of human operation and maintenance and high cost of resources faced by converter station equipment in the current new power system, this work studies and proposes an intelligent converter station anomaly collaborative processing method. Based on the data set of the existing data structure of the converter station, the operation of the power equipment is monitored by the sensor equipment. According to the abnormal signal and the designed fault analysis technology and knowledge graph, the fault intelligent analysis and fault disposal strategy are realized. The experimental results show that the proposed method can effectively monitor the abnormal data in the intelligent converter station and realize efficient fault collaborative processing.

Penerapan Data Driven Decision Making dalam Perspektif Pemilik dan Operator Kapal

The maritime industry’s crucial role in the global economy is vital, serving as the lifeline for the distribution of commercial goods worldwide. Data-Driven Decision Making (DDDM) in the maritime sector has the potential to be a game changer. By utilizing data obtained from sensors, communication tools, and integrated systems, operators can optimize fleets, improve fuel efficiency, and enhance maintenance scheduling. From the perspective of ship owners/operators, decisions regarding scheduling, operations, docking, and crew management are prioritized to ensure company profitability. Current business practices necessitate exploring the benefits of using DDDM in decision-making for ship owners/operators. The use of Big Data and DDDM approaches offers advantages such as cost efficiency and improved fleet performance. Data collection and analysis in the maritime sector include various methods, such as Automatic Identification Systems (AIS), weather data, and onboard sensor equipment. Implementing DDDM presents several challenges from the perspective of ship owners/operators, including data quality and availability, system integration, high implementation costs, regulatory compliance, and resistance to change.

Research and Practice of IoT Technology based on Smart Campus

This paper designs and implements an Internet of Things (IoT) student arrival management system based on smart campus, and uses big data technology to solve the problems of information lag and inaccuracy in traditional management mode. The system uses IoT technologies such as RFID and NFC to realize real-time monitoring and recording of students' arrival at school. By deploying sensor equipment and developing user interface, the system collects, processes and analyzes students' arrival information in real time, and provides convenient services for teachers, students and parents. This paper introduces the design and implementation process of the system in detail, including key technical points, system architecture, functional modules, implementation and testing. The practical application shows that the system significantly improves the efficiency of campus management and promotes the communication and cooperation between home and school. The challenges encountered in the implementation of the system are analyzed, and the corresponding countermeasures are put forward. This study highlights the unique advantages and broad application prospects of student arrival IoT management system integrating big data under the background of smart campus.

Collision-free tracking for a mobile robot based on purely geometric planning

A purely geometric planning method for a mobile robot in unknown environments is proposed to ensure collision avoidance with obstacles within the safety time interval while moving toward the goal. The robot initially detects a point cloud of obstacles using a 2D LiDAR. Euclidean clustering is employed to classify the point cloud into distinct point classes. Each point class is then identified as a directed closed-loop rectangle representing the obstacle. A relative orientation kd-tree is designed to store the vertices of the obstacles and determine which obstacles should be considered in the obstacle avoidance algorithm. A velocity divider is introduced to obtain a linear convex area of possible obstacle avoidance velocities. Linear planning is then used to calculate the optimal obstacle avoidance velocity for control. A virtual reference point method is proposed to address the problem of an unreachable goal in a singular configuration. Experimental results show that the directed closed-loop rectangle and relative orientation kd-tree facilitate rapid updates of required obstacle points with low-cost sensor equipment. A deterministic path for a given scenario is demonstrated, confirming the reliability of the geometric planning method for the obstacle avoidance velocity region and the optimal obstacle avoidance velocity. The proposed algorithm is further validated in scenarios with multiple obstacles and dynamic environments involving moving obstacles.

Smart Farm Control System Using IoT

This paper presents a way to do smart agriculture by using the advances in technology and information today, especially the Internet of Things (IoT) to help control the environment to change according to the needs of plants automatically. Which this research used the method of making a closed house or Greenhouse size 6m x 9m x 4m in number of 2 houses and using various types of sensor equipment. To detect parameters that affect the environment such as: Temperature sensor, Humidity sensor, Soil moisture sensor, pH sensor and Light sensor. To bring those values ​​forward to the microcontroller to process and order the electrical equipment to work, such as solenoid valves or water pumps; As well as send the parameter value to display the results to the application on the smartphone and the website through the wireless Internet system (WiFi) using the Blynk platform or Blynk cloud. From the results of the design and experiment, it was found that the system can control electrical equipment in the farm system, such as solenoid valves, water pump, and read various values ​​according to the set goals and objectives. We can order control Turn on and off the water system or the fog system anywhere at any time according to the conditions of the internet connection or direct control through the control box at any place or choose to have the system work automatically such as watering and misting according to the conditions we want and the system can also monitor or check the temperature, touch moisture, soil moisture, light intensity and pH value of the water at any time through the platform of the brand that can be used on both smartphones and computers.

Sensor based interactive digital entertainment and gamified training to alleviate basketball player fatigue

In recent years, due to the increasing number of basketball games and training activities, basketball players often face the problem of fatigue and injury. This study aims to develop an interactive digital entertainment and gamification training method to provide basketball players with more efficient training methods and enhance their training fun. Sensors can be installed in various key parts of the athlete’s body, through the use of high-precision sensor equipment, real-time acquisition of athlete action data, the use of machine learning and data mining technology, real-time analysis and modeling of sensor data to extract key information and movement patterns. Using gamified training theory to design interactive digital entertainment system, develop a series of training scenarios and gamified tasks for different technical elements, combine sensor data and motion analysis results, and provide athletes with personalized training plans and feedback mechanisms to help them improve their technical level. Through an interactive digital entertainment system, basketball players can train and compete in a virtual environment. They can complete various training tasks by interacting with the system, which will give real-time evaluation and guidance based on the athlete’s performance to help them correct mistakes, improve technique and improve training results.

Recent Advances in Machine Learning Assisted Hydrogel Flexible Sensing

AbstractHydrogel flexible sensors are widely used in wearable devices, health care, intelligent robots and other fields due to their excellent flexibility, biocompatibility and high sensitivity. With the development of single sensor to multi‐channel and multi‐mode sensor network, the sensor data also presents the characteristics of multi‐dimension, complex and massive. Traditional data analysis methods can no longer meet the data analysis requirements of hydrogel flexible sensor networks. The introduction of machine learning (ML) technology optimizes the process of data analysis. With the continuous development of multi‐layer neural network technology and the improvement of computer performance, deep learning (DL) algorithm is increasingly used to achieve higher efficiency and accuracy, provides a powerful tool for data analysis of hydrogel flexible sensor, and accelerates the intelligent process of hydrogel flexible sensor equipment. This paper introduces the classification of hydrogel flexible sensors and the working mechanism and common algorithms of ML, and summarizes the application of ML technology to assist hydrogel flexible sensors in data analysis in the fields of health care and information recognition. This review will provide inspiration and reference for integrating ML technology into the field of hydrogel flexible sensors.

Achieving local differential location privacy protection in 3D space via Hilbert encoding and optimized random response

The widespread use of spatial location-based services not only provides considerable convenience, but also exposes the downsides of location privacy leakage. Most of the existing user-side location privacy protection techniques are limited to planar locations. However, the extensive use of aircraft, sensor equipment and acquisition devices with positioning functions promotes the urgency of protecting the privacy of 3D spatial locations. Therefore, this study suggests a local differential privacy protection approach for 3D spatial locations. A 3D spatial decomposition and Hilbert encoding method are designed to reduce the 3D location data into one-dimensional encoding. The optimized random response mechanism was utilized to perturb the dimensional-reduced location encoding, which not only achieves user-side location privacy protection but also improves the accuracy of aggregated data on the server-side. Experiments on the real spatial location datasets show that the suggested method can reduce spatial location service quality loss, maintain the availability of perturbed spatial location and improve the operation efficiency of the spatial location perturbation algorithm.

Object Tracking Using Computer Vision: A Review

Object tracking is one of the most important problems in computer vision applications such as robotics, autonomous driving, and pedestrian movement. There has been a significant development in camera hardware where researchers are experimenting with the fusion of different sensors and developing image processing algorithms to track objects. Image processing and deep learning methods have significantly progressed in the last few decades. Different data association methods accompanied by image processing and deep learning are becoming crucial in object tracking tasks. The data requirement for deep learning methods has led to different public datasets that allow researchers to benchmark their methods. While there has been an improvement in object tracking methods, technology, and the availability of annotated object tracking datasets, there is still scope for improvement. This review contributes by systemically identifying different sensor equipment, datasets, methods, and applications, providing a taxonomy about the literature and the strengths and limitations of different approaches, thereby providing guidelines for selecting equipment, methods, and applications. Research questions and future scope to address the unresolved issues in the object tracking field are also presented with research direction guidelines.

Polarization insensitive multiband metamaterial absorber for bio-plastic sensing application

This article introduces a microwave multiband metamaterial absorber (MA) with high potential for bio-plastic sensing applications. The innovative design is realized through a compact unit cell dimension of 1.33λο × 1.33λο × 0.22λο, employing a state-of-the-art split-ring resonator structure. Strikingly, this absorber demonstrates polarization insensitivity and can be characterized by five distinct absorption peaks at 18.69 GHz, 23.34 GHz, 25.72 GHz, 32.94 GHz, and 35.40 GHz. The corresponding absorption rates are exceptionally high, ranging from 92.82% to 99.95%. To elucidate the underlying absorption mechanism, detailed analyses of the electric field, magnetic field, surface current distribution, and input impedance are provided, showcasing the absorber's effective MA structure. The designed MA sensor exhibits outstanding performance metrics for bio-plastic detection, including an average quality factor (Q-factor) of 210 and sensitivity of 0.888 GHz/RIU (refractive index unit), marking a significant advancement in the field. Additionally, the sensor's linearity, output variation, and sensitivity are considerably improved for bio-plastic sensing. The research confirms the proposed MA absorber's functionality by comparing measured results and simulation outcomes, indicating a high degree of accuracy and reliability. The potential applications of this MA are manifold, extending to microwave absorption and enhanced plastic sensing techniques. Its compact and thin design facilitates seamless integration with various sensor equipment, broadening the scope of its utility. Furthermore, the article delves into the relevance of this research to several Sustainable Development Goals (SDGs), particularly highlighting its alignment with SDG 9 (Industry, Innovation, and Infrastructure), SDG 12 (Responsible Consumption and Production), and SDG 14 (Life Below Water). Thus, the innovative MA design signifies a technological leap in the field of metamaterial absorbers and contributes to the pursuit of sustainability and environmental protection.

Progress in Ski Jumping Technology Based on Biomechanical Sport Research Methods

(1) Background: Previous studies have compared research into ski jumping in different motor processes, but there is a lack of comparative analysis of the biomechanical research methods used to investigate different ski jumping sports. (2) Content: Our study compared the advantages and disadvantages of six research methods and proposes future research directions. Motion video collection and analysis show that controlling angular momentum and achieving stable flight attitude in the take-off process are the most critical factors in ski jumping performance. Most research on force platforms focuses on dynamic performance at the time of take-off, but there are few training sites with an embedded force platform, and so, more empirical research is required. Wearable inertial measurement units, including gyroscopes and accelerometers, can be used to determine a series of forces, calculate the joint angle, and speculate the position of the centroid during motion. Surface EMG studies are primarily used to compare the activity characteristics of the lower limb muscles in the actual field of the jump, the exercise simulation, and the lack of complete training process data. Wind tunnel measurement can satisfy fluid mechanics simulation experiments and provide theoretical support for optimizing special ski jumping technology. Based on the theory of computational fluid dynamics, the optimal drag reduction posture data of ski jumpers can be derived using computer simulations. (3) Conclusions: Due to the wide range of ski jumping sports, the present research focused on the kinematics and dynamics of different movement stages, lacking the study of the complete exercise training process. The range of wearable inertial measurement and sensor equipment can cover the whole process of ski jumping, including kinematics and dynamics data, and is a feasible and reliable test method for monitoring ski jump training in natural environments. The simultaneous testing of surface electromyography, kinematics, and dynamics requires further exploration. (4) Future direction of development: Under computational fluid dynamics, wearable inertial measurement units and global navigation satellite systems (GNSSs), intelligent wind tunnel experimental training areas will become essential tools for ski jumping research.

Mitigating land fire disasters: Implementation of agricultural land fire risk management information system in Aunupe Village, South Konawe Regency

Climate change, which causes increased temperatures, prolonged droughts, and dry conditions, heightens the risk of land fires. A similar scenario unfolded in Aunupe Village, where several fires occurred on agricultural land over the past three years, resulting in crop failure and degraded soil quality, leading to financial losses for land-owning farmers. To mitigate the risk of land fire disasters, an agricultural land fire disaster risk management information system is necessary in Aunupe Village, South Konawe Regency. The objective of this community-based empowerment program is to mitigate the risk of land fire disasters. To achieve the desired outcomes, initial coordination with farmer group partners is conducted, followed by the design and installation of fire sensor equipment sets in collaboration with farmer groups. Furthermore, focus group discussions (FGD) are conducted with farmer group partners to ensure their understanding and cooperation. The activities result in the development of an agricultural land fire risk management information system, facilitating the prompt detection, monitoring, and response to fire incidents in the agricultural land of the Lembah Harapan Farmers Group. Additionally, farmer group partners acquire knowledge regarding the utilization of fire mitigation systems.

Multi-source adaptive thresholding adaboost with application to virtual metrology

ABSTRACT To maintain high-quality semiconductor wafer production processes, it is necessary to build high-quality virtual metrology (VM) model. Based on the result of the VM, the engineer can monitor and control the specific process. In the manufacturing process, various sources are obtained from sensor equipment. It is important to consider that these source data exhibit varying characteristics during the model construction. However, when all data sources are simply aggregated into a single model, the performance of the overall model may degrade, especially if any of the individual sources contain outliers or noise. To address this issue, we develop a data-fusion model designed to incorporate diverse data sources into a unified multi-source model. In particular, we improve an Adaboost regression algorithm to make it suitable for multi-source data in the field of VM. The algorithm combines the residuals of the models derived from each individual data source and all sources to adaptively adjust the thresholding value, which, in turn, determines whether the predicted values are accurate or not for each weak learner. Extensive practical validations on real-world processing data from semiconductor manufacturers have demonstrated that the proposed method outperforms single learning algorithms and is more robust than all benchmarks.

Non-Invasive Identification of Vehicle Suspension Parameters: A Methodology Based on Synthetic Data Analysis

In this study, we introduce an innovative approach for the identification of vehicle suspension parameters, employing a methodology that utilizes synthetic and experimental data for non-invasive analysis. Central to our approach is the application of a basic local optimization algorithm, chosen to establish a baseline for parameter identification in increasingly complex vehicle models, ranging from quarter-vehicle to half-vehicle (bicycle) models. This methodology enables the accurate simulation of the vehicle dynamics and the identification of suspension parameters under various conditions, including road perturbations such as speed bumps and curbs, as well as in the presence of noise. A significant aspect of our work is the ability to process real-world data, making it applicable in practical scenarios where data are obtained from onboard sensor equipment. The methodology was developed in MatLab, ensuring portability across platforms that support this software. Furthermore, the study explores the application of this methodology as a tool for denoising, enhancing its utility in real-world data analysis and predictive maintenance. The findings of this research provide valuable insights for vehicle suspension design, offering a cost-effective and efficient solution for dynamic parameter identification without the need for physical disassembly.

A Low-Cost and High-Precision Underwater Integrated Navigation System

The traditional underwater integrated navigation system is based on an optical fiber gyroscope and Doppler Velocity Log, which is high-precision but also expensive, heavy, bulky and difficult to adapt to the development requirements of AUV swarm, intelligence and miniaturization. This paper proposes a low-cost, light-weight, small-volume and low-computation underwater integrated navigation system based on MEMS IMU/DVL/USBL. First, according to the motion formula of AUV, a five-dimensional state equation of the system was established, whose dimension was far less than that of the traditional. Second, the main source of error was considered. As the velocity observation value of the system, the velocity measured by DVL eliminated the scale error and lever arm error. As the position observation value of the system, the position measured by USBL eliminated the lever arm error. Third, to solve the issue of inconsistent observation frequencies between DVL and USBL, a sequential filter was proposed to update the extended Kalman filter. Finally, through selecting the sensor equipment and conducting two lake experiments with total voyages of 5.02 km and 3.2 km, respectively, the correctness and practicality of the system were confirmed by the results. By comparing the output of the integrated navigation system and the data of RTK GPS, the average position error was 4.12 m, the maximum position error was 8.53 m, the average velocity error was 0.027 m/s and the average yaw error was 1.41°, whose precision is as high as that of an optical fiber gyroscope and Doppler Velocity Log integrated navigation system, but the price is less than half of that. The experimental results show that the proposed underwater integrated navigation system could realize the high-precision and long-term navigation of AUV in the designated area, which had great potential for both military and civilian applications.

Current situation of tobacco industry carbon emissions based on sensor equipment monitoring and cloud computing and optimization of ‘light storage, straight and flexible’ carbon neutralization path

Current situation of tobacco industry carbon emissions based on sensor equipment monitoring and cloud computing and optimization of ‘light storage, straight and flexible’ carbon neutralization path

Annular one-dimensional photonic crystals for salinity sensing

The use of annular one-dimensional (1D) photonic crystals (PCs) for salinity sensing is studied in this research. Annular 1D-PCs provide small and integrated structures that facilitate the creation of portable and miniaturized sensor equipment appropriate for field use. In order to generate annular 1D-PCs, the research explores the finite element method (FEM) simulation technique utilizing the COMSOL Multiphysics approach, highlighting the significance of exact control over layer thickness and uniformity. Furthermore, we construct a 1D annular PCs structure in the form {(AB)}^{N}, where A is silicon (Si) and B is silicon dioxide ({SiO}_{2}) of 40 nm and 70 nm, respectively, with a number of periods equal to 9. By incorporating a central defect layer of saline water (220 nm thickness), the sensor achieves optimum performance at normal incidence with a sensitivity (S) of 782 (nm/RIU), a quality factor (Q) of 10.22, and a figure of merit (FOM) of 12.6 {RIU}^{-1}. The design that is suggested has several advantages over past work on planners and annular 1D-PCs, including ease of implementation, performance at normal incidence, and high sensitivity.

A RGB-Thermal based adaptive modality learning network for day–night wildfire identification

Wildfires have long been a danger to the atmosphere and ecological environment. With the advancement of deep learning technology and sensor equipment, wildfire identification methods based on optical (RGB) or thermal infrared (TIR) images have made significant progress. However, single-modal identification technologies often experience serious performance degradation in challenging scenarios. Therefore, a multi-modal framework that combines both RGB and TIR is necessary for accurate wildfire identification. Despite this, current RGB-T based identification methods focus solely on developing fusion strategies to learn shared representations of the two modalities, while ignoring the effect of modality-specific features. To address this issue, we propose a novel wildfire identification framework that can adaptively learn modality-specific and shared features. Specifically, our model utilizes two parallel encoders to extract multi-scale RGB and TIR features, and integrates these modality-specific features into the fusion feature layer. Each modality-specific decoder and shared decoder corresponds to three independent label supervisions that oversee feature adaptive learning. To validate the effectiveness of our approach, we propose a new RGB-T paired wildfire semantic segmentation dataset that includes flames of different scales captured under varying lighting conditions from multiple UAV-based and ground-based cameras. Finally, we evaluate our proposed method alongside benchmarking single-modal methods and state-of-the-art multi-modal methods on two tasks: a common test setting under various lighting conditions, and a generalization test across three subsets. The experimental results demonstrate the superiority of our proposed method, with the average ＋6.41% (IoU) and ＋3.39% (F1-score) improvement over the second-best RGB-T semantic segmentation method.