Positioning Success Rate Research Articles

Deep Learning-Based Emergency Rescue Positioning Technology Using Matching-Map Images

Smartphone-based location estimation technology is becoming increasingly important across various fields. Accurate location estimation plays a critical role in life-saving efforts during emergency rescue situations, where rapid response is essential. Traditional methods such as GPS often face limitations in indoors or in densely built environments, where signals may be obstructed or reflected, leading to inaccuracies. Similarly, fingerprinting-based methods rely heavily on existing infrastructure and exhibit signal variability, making them less reliable in dynamic, real-world conditions. In this study, we analyzed the strengths and weaknesses of different types of wireless signal data and proposed a new deep learning-based method for location estimation that comprehensively integrates these data sources. The core of our research is the introduction of a ‘matching-map image’ conversion technique that efficiently integrates LTE, WiFi, and BLE signals. These generated matching-map images were applied to a deep learning model, enabling highly accurate and stable location estimates even in challenging emergency rescue situations. In real-world experiments, our method, utilizing multi-source data, achieved a positioning success rate of 85.27%, which meets the US FCC’s E911 standards for location accuracy and reliability across various conditions and environments. This makes the proposed approach particularly well-suited for emergency applications, where both accuracy and speed are critical.

A fully automatic curve localization method for extracted spine

The automation of scoliosis positioning presents a challenging and often understated task, yet it holds fundamental significance for the automated analysis of spinal morphological anomalies. This paper introduces a novel spinal curve localization model for precisely differentiating the spinal curves and identifying their concave centers. The proposed model contains three components: i) custom spine central line model, to define the spine central line as a combination of several secant line sequences with different polarities; ii) custom curve model, to classify each spinal curve into one of 11 curves types and deduce each its concave centers by several custom formulas; and iii) adapted distance transform and quadratic line fitting algorithm coupled with custom secant line segment searching strategy (DTQL-LS), to search all line segments in the spine and group consecutive line segments with identical polarity into line sequence. Experimental results show that its positioning success rate is close to 99%. Furthermore, it exhibits significant time efficiency, with the average time to process a single image being less than 30 milliseconds. Moreover, even if some image boundaries are blurred, the center of the curve can still be accurately located.

COMPARISON OF THREE MIDAZOLAM-BASED SEDATION PROTOCOLS IN BUDGERIGARS (MELOPSITTACUS UNDULATUS) AND BLACK-CHEEKED LOVEBIRDS (AGAPORNIS NIGRIGENIS).

This randomized, crossover study evaluated three sedation protocols administered subcutaneously in nine budgerigars (Melopsittacus undulatus) and nine black-cheeked lovebirds (Agapornis nigrigenis). All protocols included midazolam (5 mg/kg), combined with butorphanol (5 mg/kg) (BM), medetomidine (20 lg/kg) (MM), or alfaxalone (13 mg/kg) (AM). Mortalities from suspected cardiorespiratory arrest were observed when AM was used in lovebirds, even after reduction of alfaxalone dosage to 3 mg/kg, and therefore this protocol was excluded from further use in this species. Induction and recovery times were recorded and their quality assessed. Sedation depth and heart and respiratory rates were measured every 5 min and radiographic positioning was attempted at 10 and 20 min. At 30 min, midazolam and medetomidine were reversed with flumazenil (0.05 mg/kg, SC), and atipamezole (0.2 mg/kg, SC), respectively. MM consistently provided deep sedation in both species, with successful radiographic positioning at every attempt. As expected, heart rate was often lower with MM than with other protocols, but no associated complications were noted. In budgerigars, BM had the lowest radiographic positioning success rate (10 min: 5/9, 20 min: 3/9), whereas in lovebirds it provided significantly deeper sedation (P < 0.001), allowing radiographic positioning in all subjects. In both species, BM provided the shortest recovery times. AM resulted in reliable radiographic positioning of all budgerigars at 10 min, but not at 20 min (5/ 9), and provided consistently poor recoveries. This study highlights how differently two psittacine species of similar size may react to the same sedation protocols. AM sedation cannot be fully reversed and produced significant undesirable effects, several of which have been previously reported with alfaxalone administration to avian species. The authors therefore caution against using alfaxalone-midazolam combinations in budgerigars and black-cheeked lovebirds. Both BM and MM provided reliable sedation in these species, and appear to be suitable alternatives to AM.

Computed Tomography-guided Percutaneous Lung Biopsy With Electromagnetic Navigation Compared With Conventional Approaches: An Open-label, Randomized Controlled Trial.

The purpose of this study was to assess the efficiency and safety of computed tomography (CT)-guided percutaneous biopsy of lung lesions with electromagnetic (EM) navigation and compare them with those of conventional approaches. Seventy-nine patients with lung or liver lesions who needed biopsies were enrolled in this trial. All patients were randomly assigned to the E group underwent CT-guided percutaneous biopsies with the EM navigation system or to the C group treated with conventional approaches. In total, 27 patients with lung lesions were assigned to the E group, and 20 patients were assigned to the C group. The diagnostic success rate was 92.6% and 95% in both groups, respectively ( P >0.9999). The median number of needle repositions in the E group was less than that in the C group (2.0 vs. 2.5, P =0.03). The positioning success rate with 1 or 2 needle repositions for the E group was significantly higher than the C group (81.5% vs. 50%, P =0.03). The median accuracy of the puncture location in the E group was better than that in the C group (2.0 vs. 6.6mm, P <0.0001). The total procedure time lengthened in the E group compared with the C group (30.5±1.6 vs. 18.3±1.7min, P <0.0001), but the number of CT acquisitions was not significantly different ( P =0.08). There was no significant difference in complication incidence between the 2 groups ( P =0.44). The EM navigation system is an effective and safe auxiliary tool for CT-guided percutaneous lung biopsy, but lengthen the procedure time. ChiCTR2100043361, registered February 9, 2021-retrospectively registered ( http://www.medresman.org.cn/uc/project/projectedit.aspx?proj=7591 ).

Realtime Picking Point Decision Algorithm of Trellis Grape for High-Speed Robotic Cut-and-Catch Harvesting

For high-speed robotic cut-and-catch harvesting, efficient trellis grape recognition and picking point positioning are crucial factors. In this study, a new method for the rapid positioning of picking points based on synchronous inference for multi-grapes was proposed. Firstly, a three-dimensional region of interest for a finite number of grapes was constructed according to the “eye to hand” configuration. Then, a feature-enhanced recognition deep learning model called YOLO v4-SE combined with multi-channel inputs of RGB and depth images was put forward to identify occluded or overlapping grapes and synchronously infer picking points upwards of the prediction boxes of the multi-grapes imaged completely in the three-dimensional region of interest (ROI). Finally, the accuracy of each dimension of the picking points was corrected, and the global continuous picking sequence was planned in the three-dimensional ROI. The recognition experiment in the field showed that YOLO v4-SE has good detection performance in various samples with different interference. The positioning experiment, using a different number of grape bunches from the field, demonstrated that the average recognition success rate is 97% and the average positioning success rate is 93.5%; the average recognition time is 0.0864 s; and the average positioning time is 0.0842 s. The average positioning errors of the x, y, and z directions are 2.598, 2.012, and 1.378 mm, respectively. The average positioning error of the Euclidean distance between the true picking point and the predicted picking point is 7.69 mm. In field synchronous harvesting experiments with different fruiting densities, the average recognition success rate is 97%; the average positioning success rate is 93.606%; and the average picking success rate is 92.78%. The average picking speed is 6.18 s×bunch−1, which meets the harvesting requirements for high-speed cut-and-catch harvesting robots. This method is promising for overcoming time-consuming harvesting caused by the problematic positioning of the grape stem.

Recognition and Positioning of Fresh Tea Buds Using YOLOv4-lighted + ICBAM Model and RGB-D Sensing

To overcome the low recognition accuracy, slow speed, and difficulty in locating the picking points of tea buds, this paper is concerned with the development of a deep learning method, based on the You Only Look Once Version 4 (YOLOv4) object detection algorithm, for the detection of tea buds and their picking points with tea-picking machines. The segmentation method, based on color and depth data from a stereo vision camera, is proposed to detect the shapes of tea buds in 2D and 3D spaces more accurately than using 2D images. The YOLOv4 deep learning model for object detection was modified to obtain a lightweight model with a shorter inference time, called YOLOv4-lighted. Then, Squeeze-and-Excitation Networks (SENet), Efficient Channel Attention (ECA), Convolutional Block Attention Module (CBAM), and improved CBAM (ICBAM) were added to the output layer of the feature extraction network, for improving the detection accuracy of tea features. Finally, the Path Aggregation Network (PANet) in the neck network was simplified to the Feature Pyramid Network (FPN). The light-weighted YOLOv4 with ICBAM, called YOLOv4-lighted + ICBAM, was determined as the optimal recognition model for the detection of tea buds in terms of accuracy (94.19%), recall (93.50%), F1 score (0.94), and average precision (97.29%). Compared with the baseline YOLOv4 model, the size of the YOLOv4-lighted + ICBAM model decreased by 75.18%, and the frame rate increased by 7.21%. In addition, the method for predicting the picking point of each detected tea bud was developed by segmentation of the tea buds in each detected bounding box, with filtering of each segment based on its depth from the camera. The test results showed that the average positioning success rate and the average positioning time were 87.10% and 0.12 s, respectively. In conclusion, the recognition and positioning method proposed in this paper provides a theoretical basis and method for the automatic picking of tea buds.

Warehouse Drone: Indoor Positioning and Product Counter with Virtual Fiducial Markers

The use of robotic systems in logistics has increased the importance of precise positioning, especially in warehouses. The paper presents a system that uses virtual fiducial markers to accurately predict the position of a drone in a warehouse and count items on the rack. A warehouse scenario is created in the simulation environment to determine the success rate of positioning. A total of 27 racks are lined up in the warehouse and in the center of the space, and a 6 × 6 ArUco type fiducial marker is used on each rack. The position of the vehicle is predicted by supervised learning. The inputs are the virtual fiducial marker features from the drone. The output data are the cartesian position and yaw angle. All input and output data required for supervised learning in the simulation environment were collected along different random routes. An image processing algorithm was prepared by making use of fiducial markers to perform rack counting after the positioning process. Among the regression algorithms used, the AdaBoost algorithm showed the highest performance. The R2 values obtained in the position prediction were 0.991 for the x-axis, 0.976 for the y-axis, 0.979 for the z-axis, and 0.816 for the γ-angle rotation.

Hybrid Strategy Improved Grey Wolf Optimization Algorithm for Plume Tracking and Localization Method in Indoor Weak Wind Environment

Reliable tracking of the plume by the robot is the key to achieving plume source localization. To address the problem of low success rate and long search time of robot source location due to the unavailability of reliable information on gas diffusion flow direction and flow velocity in an indoor weak wind environment, a hybrid strategy is proposed to improve the grey wolf optimization algorithm for robot plume tracking and location. The plume is modeled using Computational Fluid Dynamics (CFD) in a two-dimensional indoor weak wind environment, and the plume concentration value is used as the individual adaptation degree of the algorithm. Without carrying plume velocity and flow direction sensors, the source-finding robot simulates the grey wolf population’s social mechanism and hunting behavior to update its position. The improved Grey Wolf Optimization algorithm is compared with the traditional Grey Wolf Optimization (GWO), Particle Swarm Algorithm (PSO), and Genetic Algorithm (GA) in simulation experiments. The simulation experiments show that the average number of iterations of the improved GWO is 7, 108, and 118 times shorter than the four source finding algorithms of GWO, PSO, and GA. The average planning path is reduced by 0.91 meters, 2.35meters, and 2.90 meters. 3s, 10.3s, and 9.3s reduce the average running time. The average positioning success rate is improved by 30%, 32%, and 40%. The applicability and Stability of the improved GWO algorithm in solving the plume tracking and localization problem in an indoor weak wind environment are verified.

The application value of computed tomography in combination with intraoperative noninvasive percutaneous ultrasonic localisation of subpleural pulmonary nodules/ground-glass opacity in uniportal video-assisted thoracoscopy.

IntroductionThis study investigates the application value of preoperative noninvasive computed tomography (CT) localisation, combined with intraoperative percutaneous ultrasonic localisation, in the precise positioning and excision of subpleural pulmonary nodules/ground-glass opacity in uniportal video-assisted thoracoscopic surgery (U-VATS).AimTo derive the precise positioning and excision of subpleural pulmonary nodules by CT combined with intraoperative percutaneous ultrasonic localisation and to avoid the complications caused by preoperative CT-guided puncture localisation, reduce physiological and psychological stress such as anxiety, CT radiation dose, and treatment cost, and to improve the treatment satisfaction of patients.Material and methodsA total of 54 patients with subpleural pulmonary nodules/ground-glass opacity (SPN/GGO), who were treated in our hospital from June 2017 to January 2020, were enrolled in this study. The patients were randomly divided into a treatment group (n = 23), and the nodules were scanned by high-resolution CT and marked at the shortest distance on the surface of the body prior to surgery. These pulmonary nodules were relocated by ultrasound at the original CT positioning points in the same body position following the administration of general anaesthesia. Then, the hookwire puncture location was performed under real-time guidance. For the control group (n = 31), the subpleural pulmonary nodules were located by CT-guided puncture and embedding a hookwire prior to surgery. Pulmonary wedge resection was performed by U-VATS in each group. The subpleural nodules were confirmed by the naked eye and rapid pathological diagnosis after surgery. The difference in positioning success rate, positioning time, the incidence of complications, and patient anxiety scores for subpleural pulmonary nodules were compared and analysed between the two groups.ResultsA total of 22 cases of subpleural nodules were successfully located in the treatment group at a success rate of 95.6% (22/23). The average positioning time for CT in combination with ultrasound was 22.0 ±5.9 min. In the control group, 31 cases of subpleural pulmonary nodules were satisfactorily located at a success rate of 100% (31/31). The average positioning time of CT was 24.2 ±5.4 min. The difference in positioning success rate and positioning time was not statistically significant (p = 0.24; p = 0.15) between the two groups. The incidence of complications and SAS anxiety scores in the treatment group were lower compared with the control group. The difference was statistically significant (p = 0.002; p < 0.001).ConclusionsPreoperative CT combined with intraoperative percutaneous real-time noninvasive ultrasonic localisation can accurately locate subpleural pulmonary nodules, with a high degree of safety and good tolerance in patients who are suitable for U-VATS.

Evaluation method of complex electromagnetic environment adaptability test for Beidou receiver

To accurately evaluate Beidou(BD) receivers complex electromagnetic environment adaptive capacity, based on the analysis of the working mechanism and the easy attack of the receiver, BD receiver facing war complex electromagnetic environment is constructed, simulation on the effect of signal capture and tracking is carried out, and assessment method is studied. The relationship between the positioning success rate and communication success rate of a certain type of BD receiver and electromagnetic environment complexity is given, providing BD receiver application with important reference significance.

The Coarse-Position-Free Coarse-Time Positioning Method for BDS Receiver

The Coarse-Time Positioning method is important for the quick positioning of the BeiDou Navigation Satellite System (BDS) navigation receiver in the weak signal environment. The coarse position estimation is the key technology of the Coarse-Time Positioning (CTP) for the BDS navigation receiver without coarse position assistance. In this paper, a Coarse-Position-Free Coarse-Time Positioning method based on mixed-type code phase ambiguity resolution is proposed. In this CTP method, in order to estimate the approximate position, the coarse position estimation method based on the mixed-type code phase ambiguity search is used. This method does not require any additional external auxiliary position information to complete the coarse position estimation. Based on the real observation data and dynamic simulation observation data, the test experiment is designed. According to the error of coarse position estimation, the positioning accuracy, and the success rate of the coarse-time solution, the Coarse-Position-Free Coarse-Time Positioning (CPFCTP) method of the BDS receiver based on the mixed-type code phase ambiguity resolution is evaluated. The experimental results show that, when the coarse-time deviation is within 30 s, the CPFCTP method has a success rate of over 97%. When the coarse-time deviation is within 5 s, the success rate of positioning is 100%. At the same time, the experimental results also show that, for the situation that the navigation signals of some BeiDou satellites are completely occluded, the CPFCTP method proposed in this paper can obtain the correct code phase ambiguity and still maintain a high success rate of CTP at the same time.

Performance of IR-UWB cross-layer ranging protocols under on-body channel models with body area networks

This paper deals with the positioning performance of the 3-Way ranging protocol (3-WR) in a wireless body area network (WBAN). The purpose is to propose a new cooperative algorithm to improve the number of estimated positions with a conditional permutation of the on-body anchors. To do so, we first evaluate and analyze the positioning success rate under a realistic mobility scenario and using two scheduling strategies: Broadcast single node localization (P2P-B) and aggregated and broadcast (A\&B)) with a medium access control (MAC) layer based on time division multiple access (TDMA). The 3-WR estimates the distance between two nodes placed on the body with the transmission of three packets. The wireless transmission is based on impulse radio ultra wideband (IR-UWB). However, these transactions can be lost through the WBAN channel leading into a ``bad positioning service.'' We consider a physical layer based on IR-UWB with three different channels: (1) an empirical theoretical model based on the on-body CM3 path loss channel (Anechoic chamber), (2) a simulated channel calculated by ray-tracing with the PyLayers simulator, and (3) an experimental channel model obtained by measurements. Our results show that the channel affects the positioning success rate that decreases as a function of the sensitivity threshold at the receiver. This can be solved with long and short term analysis for the choice of virtual anchors to increase the positioning performance.

Preoperative computed tomography-guided hook-wire positioning of pulmonary nodules.

This study aimed to analyze the clinical application value of computed tomography (CT)-guided hook-wire positioning before thoracoscopic surgery. Eighty-four patients who had received a thoracoscopic wedge resection of pulmonary nodules between January and December 2013 were selected. Group A consisted of 38 cases where the hook-wire positioning technique was not used, and the positioning approaches were intraoperative observation and palpation. Group B consisted of 46 cases where the hook-wire positioning technique was used. The diameter of each nodule was less than 2 cm, and all patients underwent the operation within 2 h of invasive positioning. The evaluation indexes included positioning success rate, positioning-related complications, and rate of conversion to thoracotomy. In Group A, nine patients (23.68%) underwent conversion to thoracotomy; in Group B, three patients (6.52%) did. This difference was statistically significant (P < 0.05). The average operation duration was 118 ± 21 min in Group A and 53 ± 18 min in Group B. The difference between both groups was statistically significant (P < 0.05). The average length of hospital stay of patients who underwent conversion to thoracotomy was 8.7 ± 2.2 days, and of patients who underwent thoracoscopic pulmonary wedge resection was 4.5 ± 1.6 days. This difference was statistically significant (P < 0.05). Therefore, CT-guided hook-wire positioning of pulmonary nodules before thoracoscopic surgery has clinical application value. It helps to accurately locate the pulmonary nodules, effectively lowers the rate of conversion to thoracotomy, and reduces the operation duration.

Placement of peripherally inserted central catheters in children guided by ultrasound

To compare the use of vascular Doppler ultrasound with vein visualization and palpation for positioning peripherally inserted central catheters in children and to determine the influence of these methods on the success of the first puncture attempt, catheter positioning, and time required for the accomplishment. A prospective randomized, controlled trial was conducted in a university hospital after ethical approval and was carried out among children (from birth to 18 yrs). São Paulo Hospital, São Paulo, Brazil. The sample comprises 42 peripherally inserted central catheters insertions allocated randomly into two groups: 1) an ultrasound group with 21 peripherally inserted central catheters guided by ultrasound; and 2) a control group with 21 catheters, in which the peripherally inserted central catheters were inserted using vein visualization and palpation. The procedure was performed by two trained nurses using a standard protocol for peripherally inserted central catheter insertion and ultrasound use. Ultrasound group equipment was ILook25 (Sonosite, Bothell, WA) with a 25-mm, 10- to 15-MHz linear array transducer that reaches a 4-cm depth. Success in the first puncture attempt was higher (p = .003) in the ultrasound group (90.5%) than in the control group (47.6%). The catheter positioning success rate was 85.7% in the ultrasound group and 52.4% in the control group (p = .019). The median time spent on the procedure for the ultrasound group was 20 mins, whereas it was 50 mins for the control group (p = .001). The use of ultrasound increased the successful positioning of peripherally inserted central catheters in comparison with the venous anatomic landmark visualization and palpation technique and further optimized the time spent on the procedure.

Strong coupling through optical positioning of a quantum dot in a photonic crystal cavity

Single self-assembled InAs quantum dots embedded in GaAs photonic crystal defect cavities are a promising system for cavity quantum electrodynamics experiments and quantum information schemes. Achieving controllable coupling in these small mode volume devices is challenging due to the random nucleation locations of individual quantum dots. We have developed an all optical scheme for locating the position of single dots with sub-10 nm accuracy. Using this method, we are able to deterministically reach the strong coupling regime with a spatial positioning success rate of approximately 70%. This flexible method should be applicable to other microcavity architectures and emitter systems.

Performance analysis of integrated GPS/GLONASS carrier phase-based positioning

Due to the different signal frequencies for the GLONASS satellites, the commonly-used double-differencing procedure for carrier phase data processing can not be implemented in its straightforward form, as in the case of GPS. In this paper a novel data processing strategy, involving a three-step procedure, for integrated GPS/GLONASS positioning is proposed. The first is pseudo-range-based positioning, that uses double-differenced (DD) GPS pseudo-range and single-differenced (SD) GLONASS pseudo-range measurements to derive the initial position and receiver clock bias. The second is forming DD measurements (expressed in cycles) in order to estimate the ambiguities, by using the receiver clock bias estimated in the above step. The third is to form DD measurements (expressed in metric units) with the unknown SD integer ambiguity for the GLONASS reference satellite as the only parameter (which is constant before a cycle slip occurs for this satellite). A real-time stochastic model estimated by residual series over previous epochs is proposed for integrated GPS/GLONASS carrier phase and pseudo-range data processing. Other associated issues, such as cycle slip detection, validation criteria and adaptive procedure(s) for ambiguity resolution, is also discussed. The performance of this data processing strategy will be demonstrated through case study examples of rapid static positioning and kinematic positioning. From four experiments carried out to date, the results indicate that rapid static positioning requires 1 minute of single frequency GPS/GLONASS data for 100% positioning success rate. The single epoch positioning solution for kinematic positioning can achieve 94.6% success rate over short baselines (<6 km).