Sensor-based Detection Research Articles

Sensor-Based Detection of Characteristics of Rubber Springs

Knowledge of experimentally obtained values of elastic deformations of rubber springs induced by applied compressive forces of known magnitudes is essential for the selection of rubber springs with optimal properties, which are used to dampen vibrations transmitted to the supporting parts of vibrating machines. This paper deals with the laboratory measurement of the characteristics of rubber springs using two types of sensors which sense the instantaneous value of the compressive force acting on the compressed spring. When using a strain tensometric force sensor, the magnitude of the measured pressure forces was evaluated by the DeweSoft DS-NET system, which was connected to an ethernet LAN, so the measured data could be processed, analysed and stored by any computer on the network. The characteristics of eight types of rubber springs were measured in two ways on laboratory equipment, and the spring stiffnesses were calculated from the measured data. Experiments have shown that the actual stiffnesses of rubber springs are lower compared to the values stated by the manufacturer, in the least favourable case, by 33.6%. It has been shown by measurements that at the beginning of the loading of the rubber spring, its compression is gradual, and the stiffness increases slowly, which is defined as the progressivity of the spring.

Solid-State Fluorescence Sensor Based on SNW1 Nanoparticles for the Quantification of 2,4,6-Trinitrotoluene.

Determining 2,4,6-trinitrotoluene (TNT) in aqueous solution is of great importance for public security, environment, and public health protection. The covalent organic framework (COF) based fluoresce probes are still of interest in developing the sensor-based detection systems for TNT. So, a novel fluorescence solid-state probe based on a melamine-based COF (SNW1)for TNT detection was established for the first time. A Fluorine-doped tin oxide (FTO) was used as a substrate, and COF was electrospray deposited onto its surface (SNW1@FTO). The effective parameters including the coating time, absorption, and desorption were optimized. Upon the addition of TNT, the fluorescence of SNW1 was quenched due to an acceptor-donor interaction. Therefore, the SNW1@FTO could detect TNT as a "Turn-off" sensor. The SNW1 probe showed good selectivity and sensitivity toward TNT in the range of 5 to 700 µmol L- 1. Finally, this sensor was employed to quantify TNT in real samples with satisfactory results.

Crowd Density Level Classification for Service Waiting Room Based on Head Detection to Enhance Visitor Experience

The crowd within a confined space can potentially lead to air stagnation in waiting areas. Constantly running air conditioning throughout the day to balance air circulation may result in excessive energy consumption by the building. To address this issue, Heating, Ventilating, and Air-Conditioning (HVAC) systems are employed to manage and regulate indoor energy usage. However, sensor-based detection often fails to capture human variables promptly, resulting in less accurate density readings. Camera footage proves to be more reliable than sensors in accurately detecting crowds. This research utilizes You Only Look Once version 8 (YOLOv8), a robust algorithm for object detection, particularly effective in crowd detection for images, along with Convolutional Vision Transformer (CvT) for crowd density level classification into "Normal" and "Crowded" levels. CvT enhances classification accuracy by incorporating function from Convolutional Neural Network (CNN) in model training, including receptive field, shared weights, etc. By integrating YOLOv8 and CvT, this method focuses on accurately classifying crowd density levels after identifying human presence in the waiting area (indoor). Evaluation metrics include mean Average Precision (mAP) for YOLOv8, and accuracy, precision, recall, and f1-score for CvT. This approach directly influences the management of HVAC systems.

Human Detection for the Betterment of Security System Using PIR Sensor and BLYNK App

Abstract: The Human Detection System (HDS) presented in this project utilizes Passive Infrared (PIR) sensors, Node MCU microcontroller, and the Blynk IoT app to detect human presence in a designated area, providing real-time monitoring and instant alerts. Additionally, an ESP32 module camera is integrated into the system to visually confirm detected events. Upon sensor activation, the ESP32 camera captures footage of the area, allowing users to verify the validity of the alert via a provided link accessible on mobile or laptop devices. This comprehensive approach enhances security measures by combining both sensor-based detection and visual confirmation capabilities, offering an effective solution for surveillance applications.

Advances in Sensor-Based Detection and Machine Learning for Osteoporosis: A Comprehensive Survey of Diagnostic Techniques

Abstract: One of the biggest challenges in the field of healthcare is the early identification of bone diseases. The increasing demand for diagnostic services often overwhelms current approaches, leading to increased healthcare costs, delayed identification, and patient discontent. To solve this problem, an Osteoporosis Early Detection System incorporating Biosensors and Machine Learning via the Internet of Things (IoT) is desperately needed. Osteoporosis difficulties and increased health risks are similar to congestion challenges that they might arise from delayed diagnosis. The scarcity of adequate technologies for early osteoporosis detection hinders effective healthcare delivery, especially in areas where the condition is more prevalent or during screenings that need quick identification. In order to enable prompt identification and notify medical professionals for preventive action, certain healthcare institutions have started including biosensors that can track changes in bone density. The development of these technologies could revolutionize the early diagnosis and treatment of osteoporosis and lessen the effects of the condition on patient’s health outcomes.

Progress and Challenge of Sensors for Dairy Food Safety Monitoring.

One of the most consumed foods is milk and milk products, and guaranteeing the suitability of these products is one of the major concerns in our society. This has led to the development of numerous sensors to enhance quality controls in the food chain. However, this is not a simple task, because it is necessary to establish the parameters to be analyzed and often, not only one compound is responsible for food contamination or degradation. To attempt to address this problem, a multiplex analysis together with a non-directed (e.g., general parameters such as pH) analysis are the most relevant alternatives to identifying the safety of dairy food. In recent years, the use of new technologies in the development of devices/platforms with optical or electrochemical signals has accelerated and intensified the pursuit of systems that provide a simple, rapid, cost-effective, and/or multiparametric response to the presence of contaminants, markers of various diseases, and/or indicators of safety levels. However, achieving the simultaneous determination of two or more analytes in situ, in a single measurement, and in real time, using only one working 'real sensor', remains one of the most daunting challenges, primarily due to the complexity of the sample matrix. To address these requirements, different approaches have been explored. The state of the art on food safety sensors will be summarized in this review including optical, electrochemical, and other sensor-based detection methods such as magnetoelastic or mass-based sensors.

Comparison of Sensor-Based and Audible Detection of Milking Liner Slips during Machine Milking of Dairy Cows.

On-farm milk flow meter technology facilitates real-time assessment of individual cow milking observations and could be used to detect milking liner slips during machine milking of dairy cows. Here, we compared the accuracy of on-farm milk flow meters for detecting milking liner slips with that of audible detection and that of a portable vacuum recording system. Compared to audible detection methods, the on-farm milk flow meter facilitated the detection of milking liner slips with moderate accuracy. Using the vacuum recording system as the gold standard, the milk flow meter system failed to detect most of the liner slips, leading to poor agreement between the two devices. We conclude that the on-farm milk flow meter system tested here compared well with audible detection; however, when vacuum recordings were considered, we found significant levels of under-detection. Taken together, dairy operators may use the on-farm milk flow meter system to inform adjustments of the milking machine settings and monitor milking routine performance. However, the system is not suitable for monitoring short-duration vacuum fluctuations. Future research is warranted to optimize the sensor-based detection of milking liner slips.

Ultrahigh-Throughput, Real-Time Flow Cytometry for Rare Cell Quantification from Whole Blood.

We present an ultrahigh-throughput, real-time fluorescence cytometer comprising a viscoelastic microfluidic system and a complementary metal-oxide-semiconductor (CMOS) linear image sensor-based detection system. The flow cytometer allows for real-time quantification of a variety of fluorescence species, including micrometer-sized particles and cells, at analytical throughputs in excess of 400,000 species per second. The platform integrates a custom C++ control program and graphical user interface (GUI) to allow for the processing of raw signals, adjustment of processing parameters, and display of fluorescence intensity histograms in real time. To demonstrate the efficacy of the platform for rare event detection and its utility as a basic clinical tool, we measure and quantify patient-derived circulating tumor cells (CTCs) in peripheral blood, realizing that detection has a sensitivity of 6 CTCs per million blood cells (0.000006%) with a volumetric throughput of over 3 mL/min.

Detection of insulation degradation by-products in transformer oil using ZnO coated IDC sensor

Abstract Condition monitoring of oil-immersed in-service transformers to facilitate preventive maintenance is still a challenge. Monitoring of 2-Furfuryldehyde (2-FAL), released in the transformer oil as a result of paper insulation degradation, and moisture ingress can provide insight into the health of the insulation of transformers. Since 2-FAL and moisture are high dielectric constant contamination, capacitive sensor-based detection is a potential solution. A novel Inter digital Capacitive (IDC) sensor is reported in this paper to measure the concentration of 2-FAL and moisture uses Zinc Oxide (ZnO) as a sensing film. The sensor shows good sensitivity, approximately linear characteristics, and low characteristic drift.

Visible-light-driven photoelectrochemical sensor based on conjugated microporous polymer-grafted graphene for o-aminophenol detection.

The pollutant o-aminophenol (o-AP) presents considerable risk to environmental safety, and its detection is therefore critical. Although various optical and electrochemical methods have been proposed for the detection of o-AP, there are a limited number of detection methods based on photoelectrochemical (PEC) sensors. In this study, a sensitive visible-light-driven PEC sensor was developed for o-AP detection in water. A conjugated microporous polymer (CMP)-coated graphene heterostructure (CMP-rGO) was synthesized and used to develop a PEC sensor. Under optimal conditions, the proposed sensor exhibited a high sensitivity of 0.03 μM with a wide linear range of 0.0034-37.6 μM. The PEC sensor also displayed acceptable repeatability and reproducibility, good long-term stability, and excellent recovery (98-102%). In addition, the binding patterns of CMP to o-AP and o-AP analog molecules were analyzed by molecular docking. Therefore, this study provides a new and feasible PEC sensor-based detection scheme for o-AP detection.

Recent Advances in Dietary Sources, Health Benefits, Emerging Encapsulation Methods, Food Fortification, and New Sensor-Based Monitoring of Vitamin B12: A Critical Review.

In this overview, the latest achievements in dietary origins, absorption mechanism, bioavailability assay, health advantages, cutting-edge encapsulation techniques, fortification approaches, and innovative highly sensitive sensor-based detection methods of vitamin B12 (VB12) were addressed. The cobalt-centered vitamin B is mainly found in animal products, posing challenges for strict vegetarians and vegans. Its bioavailability is highly influenced by intrinsic factor, absorption in the ileum, and liver reabsorption. VB12 mainly contributes to blood cell synthesis, cognitive function, and cardiovascular health, and potentially reduces anemia and optic neuropathy. Microencapsulation techniques improve the stability and controlled release of VB12. Co-microencapsulation of VB12 with other vitamins and bioactive compounds enhances bioavailability and controlled release, providing versatile initiatives for improving bio-functionality. Nanotechnology, including nanovesicles, nanoemulsions, and nanoparticles can enhance the delivery, stability, and bioavailability of VB12 in diverse applications, ranging from antimicrobial agents to skincare and oral insulin delivery. Staple food fortification with encapsulated and free VB12 emerges as a prominent strategy to combat deficiency and promote nutritional value. Biosensing technologies, such as electrochemical and optical biosensors, offer rapid, portable, and sensitive VB12 assessment. Carbon dot-based fluorescent nanosensors, nanocluster-based fluorescent probes, and electrochemical sensors show promise for precise detection, especially in pharmaceutical and biomedical applications.

Computer vision application for industrial Li-ion battery module disassembly

Automated robot-assisted disassembly is essential for the flexible disassembly of Li-ion battery modules for economic and safety reasons. In such a case, a CAD model for the planning process is of immense benefit. The geometric uncertainties due to the breathing of the Li-ion cells as well as the presence of component tolerances underline the importance of a sensor-based detection approach to determine the actual state of the battery module, which is crucial to ensure an automated and reliable disassembly process. In this paper, we present a method for 3D camera-based localization of points on deformed battery modules, aiding in identifying support points for milling operations in robot-assisted disassembly cells. This separation operation planning employs a CAD model, and our introduced computer vision “data processing pipeline”—a systematic series of processing steps—bridges the gap between the CAD model and the actual battery module. This involves capturing the module using a 3D camera and subsequently registering its points with the CAD model’s points. Central to this process are two algorithms: The Bayesian Coherent Point Drift (BCPD) algorithm ensures accurate non-rigid registration, while TEASER++ aids in reducing computational time. We demonstrate the effectiveness of these combined algorithms in our pipeline through rigorous testing and metrics, evidencing that a balance between accuracy and computational speed can be attained by adjusting point density.

Sensor-based detection of individual walkability perception to promote healthy communities

People living in walkable areas are more likely to maintain a physically active lifestyle. Adverse elements of the built environment (e.g., demolished houses, damaged sidewalks) can cause physical or emotional distress, and negatively affect walkability patterns. Individuals are likely to perceive walkability of a place in distinct ways and can be differentially impacted by the built environment. This paper quantifies walkability perception of the built environment using data from “in-the-moment” interactions between pedestrians and the built environment, captured by wearable physiological and accelerometry sensors. Prominent temporal change patterns in physiological reactivity (i.e., electrodermal activity, heart rate) and gait are captured through a physiological saliency cue (PSC), which comprises the input of a machine learning model automatically estimating pedestrians’ perceived walkability. Contextual information from user’s location is further used to augment the features. Results obtained on 25 participants in a field experiment indicate that the PSC measures can reliably detect individual perception of walkability, often more accurately compared to the aggregate measures from the corresponding raw signals. Inclusion of contextual information further improves the performance. Findings from this study can enhance our understanding on the association between walkability and the built environment, and lead to more effective planning and public health strategies that contribute to community health.

Video Fire Detection Methods Based on Deep Learning: Datasets, Methods, and Future Directions

Among various calamities, conflagrations stand out as one of the most-prevalent and -menacing adversities, posing significant perils to public safety and societal progress. Traditional fire-detection systems primarily rely on sensor-based detection techniques, which have inherent limitations in accurately and promptly detecting fires, especially in complex environments. In recent years, with the advancement of computer vision technology, video-oriented fire detection techniques, owing to their non-contact sensing, adaptability to diverse environments, and comprehensive information acquisition, have progressively emerged as a novel solution. However, approaches based on handcrafted feature extraction struggle to cope with variations in smoke or flame caused by different combustibles, lighting conditions, and other factors. As a powerful and flexible machine learning framework, deep learning has demonstrated significant advantages in video fire detection. This paper summarizes deep-learning-based video-fire-detection methods, focusing on recent advances in deep learning approaches and commonly used datasets for fire recognition, fire object detection, and fire segmentation. Furthermore, this paper provides a review and outlook on the development prospects of this field.

Bolts looseness detection in construction machinery

Bolt connections have increasingly wide applications in the mechanical industry, such as civil construction, construction machinery, etc. However, along with the vibration of the mechanical operation, bolt looseness is unavoidable and thus can lead to severe consequences. Therefore, the detection of loose bolts deserves an in-depth study. However, conventional bolt looseness detection techniques require a lot of time and labor, and direct contact sensor-based detection techniques are sensitive to interference from the surroundings. To tackle these challenges mentioned above, this work proposes a vision-based bolt looseness detection method, with the advantages of low cost, easy deployment, and non-contact. Specifically, an innovative attention mechanism is introduced into the Yolov4 framework to improve the accuracy and speed of bolt detection. Each bolt image is cropped by the recognition result of the detector, then the bolt contour is extracted by edge detection, and the bolt is determined to be loose or not based on the angle of bolt rotation. Comprehensive experiments in real-world settings verify the effectiveness and efficiency of the proposed method.

Trajectory planning method with grinding compensation strategy for robotic propeller blade sharpening application

A propeller is the main part of a water-borne carrier's drive system. Geometrical shape accuracy and sharpness on the cutting side of the propeller's blade play vital roles to minimize fluid resistance and improve transmission efficiency. For Jet Ski and small boats, the significant thickness variation along the blade edge is embedded in the lost-wax casting process. The automatic trajectory planning for the robotic propeller blade's sharpening operation is challenging due to its complicated curved shape and the tiny gaps between two connected blades. The trajectory planning for robotic grinding based on the edge thickness distribution of the standard model may result in over- or under-cutting due to the highly inconsistent shape deformation caused by the casting process. To address the aforementioned challenges, this study proposes a fully automated robot grinding system. The proposed method combines a novel trajectory planning approach based on a parametric and point cloud model with a 3D scanning on edge-based trajectory adjustment approach. Moreover, to improve the grinding accuracy, a laser-vision sensor-based detection algorithm is also developed for grinding compensation to counteract the geometrical variation caused by the casting process. The effectiveness of the proposed system is validated through numerous experimental trials using a 6-DOF industrial robot. The research findings showcase that the proposed technique is feasible, stable, and effective for robotic propeller blade edge sharpening operations.

Absolute maximum slope difference method for NPW real-time localization of leakage in pipelines

Pipelines provide an economical mode of transportation for hauling gas and liquids such as oil over long distances. Pipeline explosions cause massive loss of lives, and adversely impact both the environment and the economy. Accurate and automated detection of the arrival times of negative pressure waves (NPW) because of leakages is the key parameter in many pipeline leakage detection approaches. The method introduced here uses the absolute maximum difference in the slopes of NPW time-domain signals for accurate determination of the time of signal arrivals at the sensors. The proposed method involves Fiber Bragg Grating (FBG) sensor-based detection of the leakages, and determination of the arrival of NPW signals for accurate detection of the knee-points in the signals. The main advantage in using the proposed approach is determination of exact arrival time of NPW for accurate detection of leakage point locations along the lengths of pipelines. The experimental program includes construction of two separate gas and liquid pipelines for evaluation of the absolute maximum slope difference (AMSD) method. The study includes evaluation of the differences between the proposed method and conventional visual determination of the NPW arrival times, and the actual locations of the leakage sources in the experiments. The numerical approach introduced herein enables direct integration of the proposed method, for automated real-time monitoring of pipeline leakage locations.

Sensor-based detection of a Haemonchus contortus (Barber's pole worm) infection in sheep

Haemonchus contortus, or Barber's Pole worm, is considered one of the most pathogenic parasites of sheep due to the production, profitability and animal welfare implications associated with infections. However, detection of H. contortus infections by routine observation of sheep flocks is difficult, and producers are usually unaware of a problem until animals are severely infected. The aim of the current study was to explore the potential for accelerometer-based activity monitoring to detect H. contortus infections in sheep.A three-month clinical study was conducted in Central Queensland, Australia, whereby 45, 12-month-old merino wethers were randomly allocated to one of three treatment groups: control (n = 9), low H. contortus infection (n = 18) or high H. contortus infection (n = 18). Infection occurred on Day 0, and accelerometer sensors were attached to a halter and deployed on all animals from Day 21 to Day 70. Animals were sampled weekly (faecal and blood) and treated with an anthelmintic on Day 56. Following the clinical period, five study animals were observed for a total of five hours to compare direct behavioral observations against accelerometer data. This was then used to develop a machine learning (ML) model to classify the accelerometer data into active or inactive behavior, which was further summarized to determine the proportion of time spent active per day. The most valuable features in the selected ML model were movement variation (MV), maximum X-axis value (MaxX), standard deviation of the X-axis (SDX), maximum Y-axis value (MaxY) and standard deviation of the Z-axis (SDZ).Linear mixed-effects models identified a significant difference in all sheep activity pre- and post-anthelmintic drench on Day 56 (P < 0.001). Conversely, there was no significant difference between activity levels of infected animals compared to controls (P = 0.14). To further explore how the activity of sheep changed with clinical presentations of H. contortus infections, weekly faecal egg count (FEC) and blood packed cell volume (PCV) were compared to sheep activity using a Spearman's rank correlation test. There was a weak but significant negative correlation between FEC and sheep activity (P < 0.001) and a weak but significant positive correlation between PCV and sheep activity (P < 0.001).In conclusion, this study has shown that accelerometer-based activity monitoring may be able to identify changes in sheep activity associated with clinical presentations of H. contortus infections and between periods prior to and following anthelmintic treatment. However, the ability to detect activity differences between infected and control animals was less clear. Further research is needed to determine the impact of individual behavior variability and flock dynamics when using on-animal sensors for the detection of behavioral changes associated with disease.

A Small Target Forest Fire Detection Model Based on YOLOv5 Improvement

Forest fires are highly unpredictable and extremely destructive. Traditional methods of manual inspection, sensor-based detection, satellite remote sensing and computer vision detection all have their obvious limitations. Deep learning techniques can learn and adaptively extract features of forest fires. However, the small size of the forest fire target in the long-range-captured forest fire images causes the model to fail to learn effective information. To solve this problem, we propose an improved forest fire small-target detection model based on YOLOv5. This model requires cameras as sensors for detecting forest fires in practical applications. First, we improved the Backbone layer of YOLOv5 and adjust the original Spatial Pyramid Pooling-Fast (SPPF) module of YOLOv5 to the Spatial Pyramid Pooling-Fast-Plus (SPPFP) module for a better focus on the global information of small forest fire targets. Then, we added the Convolutional Block Attention Module (CBAM) attention module to improve the identifiability of small forest fire targets. Second, the Neck layer of YOLOv5 was improved by adding a very-small-target detection layer and adjusting the Path Aggregation Network (PANet) to the Bi-directional Feature Pyramid Network (BiFPN). Finally, since the initial small-target forest fire dataset is a small sample dataset, a migration learning strategy was used for training. Experimental results on an initial small-target forest fire dataset produced by us show that the improved structure in this paper improves mAP@0.5 by 10.1%. This demonstrates that the performance of our proposed model has been effectively improved and has some application prospects.

TMR Sensor-Based Detection of EVs in Semi-Dynamic Traffic for Optimal Charging

One of the challenges faced in the design of inductive power transfer (IPT) highway is the detection of electric vehicle (EV), to enable charging, as it travels along the highway. When a primary coil buried under the highway has sufficient coupling with the secondary coil mounted on the vehicle, it is energized to initiate IPT. In this paper, a tunneling magnetoresistance (TMR) sensor based EV detection method on an IPT highway is proposed. In the proposed scheme, a detection coil is wound around the outer boundary of the secondary coil and it is excited at 400 kHz. The TMR sensors are arranged close to the primary coil such that it senses the magnetic field generated by the detection coil. The TMR sensors are placed over the leading and trailing edges (in the direction of EV travel) of the primary coil. From the leading edge TMR sensor outputs, the energization point of that primary coil to begin IPT is decided. Similarly, from the trailing edge TMR sensor outputs, the de-energization point to stop IPT from that primary coil is decided. Also, the effective area of overlap between the coils due to lateral misalignment is estimated. This enables the driver in correcting the lateral misalignment so that efficient charging is possible from the subsequent primary pads. A laboratory scale prototype was built and was tested. The results obtained prove the usefulness of the scheme.