Localization Error Rate Research Articles

Map-based localization for intelligent vehicles based on fusion of multiple visual features in underground parking

The ‘last mile’ problem in intelligent car localization within underground parking lots presents challenges such as localization blind spots and feature extraction difficulties. To tackle these issues, this paper proposes a mapping and multiscale matching localization method based on the fusion of multiple feature sources using a ‘binocular mapping, monocular localization’ approach. By combining traditional features with deep learning features, the proposed method enhances feature matching accuracy and addresses feature extraction challenges. A sparse three-dimensional reconstruction method based on local feature-optical flow is also proposed to mitigate localization blind spots. During the mapping process, the underground parking lot scene is segmented into several nodes to store map information, each consisting of a feature layer, scene structure layer, and trajectory layer. In the multiscale matching localization process, ORB, LoFTR, and BoW multisource features are fused to achieve feature matching, determine the nearest node, and estimate vehicle pose using the PnP model through optical flow. Finally, a localization optimization algorithm outputs the localization result. Experiments were conducted across multiple underground parking lots encompassing a total area of over 100,000 square meters. The results demonstrated that the average error of map construction using the proposed algorithm is approximately 15 mm, and the average error rate of localization is 4.45%.

An ameliorated localization algorithm for compensating stratification effect based on improved underwater salp swarm optimization technique

SummaryThe underwater acoustic sensor network is a fundamental source for ocean exploration. The potential applications of underwater acoustic sensor network (UASN) include seismic imaging, disaster prevention, mine reconnaissance, pollution monitoring, exploration of natural resources, and military surveillance. To acquire accurate results, implementing all applications of underwater sensor networks requires an adequate network connection and communication technology. The precise placement of underwater sensor nodes needs to be identified in order to achieve effective communication. To accomplish the requirement, the paper presents an efficient localization algorithm to compensate the stratification effect based on an improved underwater salp swarm optimization technique (LAS‐IUSSOT). To compute the location of sensor nodes with high accuracy, the nodes are initially randomly deployed in three‐dimensional underwater acoustic sensor network (3D‐UASN). After that, the hybridization of centroid‐based localization and the ray theory technique is used, and then, the degree of coplanarity is analyzed among the underwater sensor nodes. Then, the computation of the location of unknown nodes is performed using improved underwater salp swarm optimization technique (IUSSOT) to obtain the optimized location and compensate the impact of the stratification. The comparison of the simulation results of the existing algorithm and the proposed algorithm is performed. The LAS‐IUSSOT achieves 40.46% and 28.00% accuracy in terms of localization of underwater sensor nodes for both the sparse and dense regions in 3D‐UASN. The LAS‐IUSSOT achieves 49.39% and 62.57% accuracy in terms of ranging of underwater sensor nodes for both the sparse and dense regions in 3D‐UASN. Simulation results illustrate that the proposed algorithm outperforms the existing algorithm in terms of localization and ranging accuracy in both sparse and dense regions in 3D‐UASN, root mean square error (RMSE), normalized localization error (NLE), computation time, and convergence rate.

A Higher-Order Singular Value Decomposition-Based Target Localization Algorithm for WiFi Array Systems

Traditional Angle of Arrival (AoA)-based WiFi array indoor localization algorithms do not fuse Channel State Information (CSI) inter-packet data for estimation, which makes WiFi arrays less effective for localization in complex indoor environments. Most algorithms are overburdened leading to inefficient localization. To address these issues, in this article, an indoor positioning algorithm based on Higher-Order Singular Value Decomposition (HOSVD) is proposed. First, the CSI data are reconstructed as a new measurement matrix by borrowing subcarriers, and a third-order tensor is constructed. Next, tensor compression techniques are used to reduce computational complexity and the signal subspace is obtained by HOSVD. Then, the AoA is obtained by the Reduced Dimension Multiple Signal Classification (RD-MUSIC) method. Finally, the coordinates of the target can be obtained by triangulating the AoAs of the three Access Points (APs). According to the simulation experiments, the AoA can be estimated accurately at a low SNR and with low snapshots. In practical experiments, we can successfully estimate the AoA in complex indoor environments with shorter timelines using HOSVD without modifications to commercial hardware and produce a lower AoA error and localization error rates compared to other algorithms. The effectiveness of our proposed algorithm is proven by simulations and practical experiments.

Comparison of a Free-Field and a Closed-Field Sound Source Identification Paradigms in Assessing Spatial Acuity in Adults With Normal Hearing Sensitivity.

Traditional sound field localization setups in a free-field environment closely represent real-world situations. However, they are costly and sophisticated, and it is difficult to replicate similar setups in every clinic. Hence, a cost-effective, portable, and less sophisticated virtual setup will be more feasible for assessing spatial acuity in the clinical setting. The virtual auditory space identification (VASI) test was developed to assess spatial acuity using virtual sources in a closed field. The present study compares the legitimacy of these two methods. Fifty-five individuals with normal hearing (mean age±SD: 21± 3.26 years) underwent spatial acuity assessment using two paradigms: 1) the sound field paradigm (localization test) and 2) the virtual paradigm (VASI test). Location-specific and overall accuracy scores and error rates were calculated using confusion matrices for each participant in both paradigms. The results of Wilcoxon signed-rank tests showed that the locationspecific and overall accuracy scores for both paradigms were not significantly different. Further, both paradigms did not yield significantly different localization error rates like right and left intra-hemifield errors, inter-hemifield errors, and front-back errors. Spearman's correlation analysis showed that all the measures of the two paradigms had mild to moderate correlation. These results demonstrate that both VASI and the sound field paradigm localization test performed equally well in assessing spatial acuity.

Constrained DNN-Based Robust Model Predictive Control Scheme with Adjustable Error Tube

This paper proposes a novel robust model predictive control (RMPC) scheme for constrained linear discrete-time systems with bounded disturbance. Firstly, the adjustable error tube set, which is affected by local error and error variety rate, is introduced to overcome uncertainties and disturbances. Secondly, the auxiliary control rate associated with the cost function is designed to minimize the discrepancy between the actual system and the nominal system. Finally, a constrained deep neural network (DNN) architecture with symmetry properties is developed to address the optimal control problem (OCP) within the constrained system while conducting a thorough convergence analysis. These innovations enable more flexible adjustments of state and control tube cross-sections and significantly improve optimization speed compared to the homothetic tube MPC. Moreover, the effectiveness and practicability of the proposed optimal control strategy are illustrated by two numerical simulations. In practical terms, for 2-D systems, this approach achieves a remarkable 726.23-fold improvement in optimization speed, and for 4-D problems, it demonstrates an even more impressive 7218.07-fold enhancement.

An Internet of Electronic-Visual Things Indoor Localization System Using Adaptive Kalman Filter

In recent years, various indoor social security emergencies have brought major changes to people’s lives. However, the state-of-art surveillance technology achieving object tracking alone is insufficient through a single visual tracking method and may cause inaccurate tracking (such as burred faces, loss target, and occlusion) and is time-consuming for a long video sequence. Accurate tracking and localization systems are essential for developing indoor localization systems. This paper designs a fusing communication system called the Internet of Electronic-Visual Things Localization system (IoEVT), which simultaneously tracks targets assisting with an Adaptive Kalman Filter (AKF). The data fusion indoor localization approach using AKF fuses multi-data from electronic (E) and visual (V) data, such as WiFi and cameras. The fusing method significantly improves EV data sensing abilities for solving occluded visual information when only using single V data in occlusion scenarios and reduces the localization error rate. In addition, our real-world experimental validation shows that the proposed IoEVT system achieves better accuracy, scalability, and robustness with low network bandwidth consumption compared with the single E or V data in many scenarios, such as occlusion and occlusion-free.

An Efficient Anchor-Free Localization Algorithm for all Cluster Topologies in a Wireless Sensor Network

A wireless sensor network is a type of network, which has many application domains such as military, civil security, industrial and environmental. Localization of fixed or mobile wireless sensors in wireless sensor networks is a delicate issue that has attracted the attention of many researchers. Indeed, a good estimation of the distances between different wireless sensors allows to derive their precise locations in the network. An ideal solution for locating these wireless sensors is to equip them with localization devices such as GPS. However, this solution is not an energy-efficient. Indeed, GPS is very energy-consuming, and the deployment environment is not easily accessible to humans. So, it is not possible to replace the batteries of these wireless sensors when they are discharged. Therefore, it is necessary to propose an energy-saving anchor-free localization algorithm. Despite the grouping of nodes into clusters (or sub-networks), existing anchor-free localization algorithms suffer from a low rate of node localization, low localization accuracy, and high energy consumption. To improve the proposed solutions in the literature, an Efficient Anchor Free Localization Algorithm (EAFLA) was proposed. Regardless the topology of each cluster, our algorithm allows localization of all wireless sensors with a very low localization error rate and consumes less energy.

An efficient 3D localization algorithm for compensating stratification effect in underwater acoustic sensor network

AbstractCommunication and networking plays a crucial role in data transmission in UASN. The sensor nodes in UASN are intermittently deployed randomly in the three‐dimension scenario. As a consequence, the three‐dimension based localization algorithm is the need for an hour. To fulfill the objective, we have proposed a localization algorithm I‐LASP (Improvement of localization algorithm for compensating stratification effect based on extended improved particle swarm optimization technique) in three‐dimensional UASN, based on compensation of stratification effect for the improvement of the performance parameters such as localization accuracy, ranging accuracy, convergence rate and execution time. To compute the accurate position of target nodes, EIPSO (Extended improved PSO) technique is applied, and the degree of coplanarity is checked before the calculation of distance among nodes in order to get the accurate location of target nodes. The Centroid method is used to initialize the position of sensor nodes, and the ray theory method is used to compensate the stratification effect on the layered ocean water. The proposed algorithm is compared to the existing LASP, Std PSO, and GNA‐ESSP (Gauss‐newton algorithm‐extended sound speed profile) localization algorithm. The proposed algorithm provides 34.50%, 38.87%, and 42.66% of high accuracy in terms of localization with low density of target sensor nodes and 37.96%, 29.58%, and 50.77% high accuracy in terms of localization with a high density of target sensor nodes respectively. The proposed algorithm is compared with LASP, GNA‐ESSP, and TDOA to obtain 66.84%, 71.14%, and 86.13% of high accuracy in terms of ranging with low density of target sensor nodes and 42.34%, 89.00%, and 95.08% high accuracy in terms of ranging with a high density of target sensor nodes respectively. Experimental results represents that the proposed algorithm obtains better performance in terms of localization accuracy, ranging accuracy, root mean square error, normalized localization error, execution time and convergence rate.

Neural stochastic differential equations network as uncertainty quantification method for EEG source localization

EEG source localization remains a challenging problem given the uncertain conductivity values of the volume conductor models (VCMs). As uncertain conductivities vary across people, they may considerably impact the forward and inverse solutions of the EEG, leading to an increase in localization mistakes and misdiagnoses of brain disorders. Calibration of conductivity values using uncertainty quantification (UQ) techniques is a promising approach to reduce localization errors. The widely-known UQ methods involve Bayesian approaches, which utilize prior conductivity values to derive their posterior inference and estimate their optimal calibration. However, these approaches have two significant drawbacks: solving for posterior inference is intractable, and choosing inappropriate priors may lead to increased localization mistakes. This study used the Neural Stochastic Differential equations Network (SDE-Net), a combination of dynamical systems and deep learning techniques that utilizes the Wiener process to minimize conductivity uncertainties in the VCM and improve the inverse problem. Results revealed that SDE-Net generated a lower localization error rate in the inverse problem compared to Bayesian techniques. Future studies may employ new stochastic dynamical systems-based techniques as a UQ technique to address further uncertainties in the EEG Source Localization problem. Our code can be found here: https://github.com/rrwabina/SDENet-UQ-ESL.

Intelligent Aquila Optimization Algorithm-Based Node Localization Scheme for Wireless Sensor Networks

In recent times, wireless sensor network (WSN) finds their suitability in several application areas, ranging from military to commercial ones. Since nodes in WSN are placed arbitrarily in the target field, node localization (NL) becomes essential where the positioning of the nodes can be determined by the aid of anchor nodes. The goal of any NL scheme is to improve the localization accuracy and reduce the localization error rate. With this motivation, this study focuses on the design of Intelligent Aquila Optimization Algorithm Based Node Localization Scheme (IAOAB-NLS) for WSN. The presented IAOAB-NLS model makes use of anchor nodes to determine proper positioning of the nodes. In addition, the IAOAB-NLS model is stimulated by the behaviour of Aquila. The IAOAB-NLS model has the ability to accomplish proper coordinate points of the nodes in the network. For guaranteeing the proficient NL process of the IAOAB-NLS model, widespread experimentation takes place to assure the betterment of the IAOAB-NLS model. The resultant values reported the effectual outcome of the IAOAB-NLS model irrespective of changing parameters in the network.

The Improvement of DV-Hop Model and Its Application in the Security Performance of Smart Campus

In the smart campus, sensors are the basic units in the whole the Internet of Things structure, which play the role of collecting information and transmitting it. How to transmits more information at a certain power level has attracted the attention of many researchers. In this paper, the DV-Hop algorithm is optimized by combining simulated annealing-interference particle swarm optimization algorithm to improve the node localization of wireless sensor networks and enhance the security performance of smart campus. To address the problem that particle swarm optimization easily falls into local optimum, a perturbation mechanism is introduced in the basic particle swarm optimization algorithm. Meanwhile, the acceptance probability P is introduced in the simulated annealing algorithm to determine whether a particle is accepted when it “flies” to a new position, which improves the probability of finding a global optimal solution. Comparing the average localization error and optimization rate of the DV-Hop algorithm, PSO-DV-Hop algorithm, and the optimized algorithm. The results show a greater advantage of the algorithm. This will greatly enhance the safety performance and efficiency of the smart campus.

Cooperative Relative Localization for UAV Swarm in GNSS-Denied Environment: A Coalition Formation Game Approach

Unmanned aerial vehicle (UAV) swarms require accurate relative localization to safeguard flight missions in the global navigation satellite system-denied environment due to a lack of absolute position information. The existing work of relative localization faces challenges, such as the ranging information loss and the low localization frequency caused by long-distance ranging and large-scale characteristic of the UAV swarm. This article proposes a clustering-based cooperative relative localization scheme for UAV swarm, which contains a two-level framework: inter/intra-cluster localization. In order to investigate the tradeoff between intracluster cooperation and intercluster packet loss, the clustering-based problem is constructed as a coalition formation game (CFG) model. Given the designed coalition value, preference relation, and the coalition formation principles, it is proved that the proposed CFG model has a Nash stable partition. The designed coalition formation algorithm includes coalition heads and beacon drones selection mechanism. Simulation results show that the proposed CFG algorithms shorten the ranging time compared with global localization and achieve better localization performance (localization error and success rate) than contrast algorithms.

A Survey of Recent Indoor Localization Scenarios and Methodologies.

Recently, various novel scenarios have been studied for indoor localization. The trilateration is known as a classic theoretical model of geometric-based indoor localization, with uniform RSSI data that can be transferred directly into distance ranges. Then, a trilateration solution can be algebraically acquired from theses ranges, in order to fix user’s actual location. However, the collected RSSI or other measurement data should be further processed and classified to lower the localization error rate, instead of using the raw data influenced by multi-path effect, multiple nonlinear interference and noises. In this survey, a large number of existing techniques are presented for different indoor network structures and channel conditions, divided as LOS (light-of-sight) and NLOS (non light-of-sight). Besides, the input measurement data such as RSSI (received signal strength indication), TDOA (time difference of arrival), DOA (distance of arrival), and RTT (round trip time) are studied towards different application scenarios. The key localization techniques like RSSI-based fingerprinting technique are presented using supervised machine learning methods, namely SVM (support vector machine), KNN (K nearest neighbors) and NN (neural network) methods, especially in an offline training phase. Other unsupervised methods as isolation forest, k-means, and expectation maximization methods are utilized to further improve the localization accuracy in online testing phase. For Bayesian filtering methods, apart from the basic linear Kalman filter (LKF) methods, nonlinear stochastic filters such as extended KF, cubature KF, unscented KF and particle filters are introduced. These nonlinear methods are more suitable for dynamic localization models. In addition to the localization accuracy, the other important performance features and evaluation aspects are presented in our paper: scalability, stability, reliability, and the complexity of proposed algorithms is compared in this survey. Our paper provides a comprehensive perspective to compare the existing techniques and related practical localization models, with the aim of improving localization accuracy and reducing the complexity of the system.

Classification of Gaussian spatio-temporal data with stationary separable covariances

The novel approach to classification of spatio-temporal data based on Bayes discriminant functions is developed. We focus on the problem of supervised classifying of the spatiotemporal Gaussian random field (GRF) observation into one of two classes specified by different drift parameters, separable nonlinear covariance functions and nonstationary label field. The performance of proposed classification rule is validated by the values of local Bayes and empirical error rates realized by leave one out procedure. A simulation study for spatial covariance functions belonging to powered-exponential family and temporal covariance functions of AR(1) models is carried out. The influence of the values of spatial and temporal covariance parameters to error rates for several label field models are studied. The results showed that the proposed classification methodology can be applied successfully in practice with small error rates and can be a useful tool for discriminant analysis of spatio-temporal data.

A Hybrid Crow Search and Gray Wolf Optimization Algorithm‐based Reliable Non‐Line‐of‐Sight Node Positioning Scheme for Vehicular Ad hoc Networks

SummaryVehicular Ad hoc NETwork (VANET) facilitates ubiquitous connectivity for establishing Vehicle‐to‐Vehicle (V2V) communication and supporting Intelligent Transportation Systems (ITSs). This vehicle communication requires complete coverage within the target range for ensuring reliable message dissemination. High density of vehicles in the intersections introduces challenges due to obstacles such as buildings, foliage, and other moving vehicles, preventing exchange of information about location and message update between vehicles. Non‐Line‐of‐Sight (NLOS) nodes also introduce broadcasting storm problem leading to congestion that prevents emergency messages from reaching the target vehicular nodes. Integration of meta‐heuristic Crow Search Algorithm (CSA) and Gray Wolf Optimization Algorithm (GWOA) minimizes the objective function of NLOS localization problem without the solution being trapped into local optima. In this paper, a Hybrid Crow Search and GWOA‐based NLOS Positioning Scheme (HCSGWOA‐NLOS‐PS) is proposed to handle the issue of broadcast storm and facilitate reliability in emergency message delivery. The proposed HCSGWOA‐NLOS‐PS utilizes the benefits of Time of Arrival (ToA) and geographical information‐based cooperative localization agent for attaining efficient NLOS node positioning in the network. It uses the benefits of CSA and GWOA for positioning the NLOS nodes based on the intelligence derived from the crows' conduit and the social attacking behavior of gray wolves that are ideal for balancing the tradeoff between exploration and exploitation. The simulation results of the proposed HCSGWOA‐NLOS‐PS confirm a mean emergency message delivery of 11.82%, neighborhood awareness of 12.38% with reduced localization error rate of 2.36% and minimized delay of 8.64% when compared to the baseline approaches.

A novel visual short‐term memory task differentiates MCI and Alzheimer’s patients from healthy ageing

AbstractBackgroundWe developed a novel delayed reproduction task, the “What was where?” task, which obtains a continuous measure of localization error and is more sensitive compared to conventional span measures of Short‐term Memory (STM).MethodWe recruited 44 MCI (Mild Cognitive Impairment), 41 AD (Alzheimer’s Disease) patients and 109 healthy elderly controls (EHCs) from memory clinics in Oxford, UK and Jena, Germany, where they performed the “What was where?” task (Figure 1). We extracted the following metrics: Identification Accuracy (percentage correctly identified items), Absolute Localization Error (how far the object was misplaced), Misbinding rate (erroneously localizing an item to the remembered location of another item in memory) and Guessing response rate.ResultAbsolute Localization Error and Misbinding rates were greater in MCI and AD patients (p < 0.001) compared to EHCs, while AD and MCI performed similarly on these metrics. However, Identification Accuracy as well as Guessing (p = 0.003) were greater in MCI (p < 0.001) compared to AD patients. Moreover, EHCs identified the correct object more often (p < 0.001) and guessed less (p < 0.001) than MCI patients.ConclusionThis novel task is able to detect STM impairment in MCI cases on a continuous scale, and is a sensitive memory measure which might be a useful index of memory for future clinical trials in AD in its earliest stages.

Effective Population Size Predicts Local Rates but Not Local Mitigation of Read-through Errors.

In correctly predicting that selection efficiency is positively correlated with the effective population size (Ne), the nearly neutral theory provides a coherent understanding of between-species variation in numerous genomic parameters, including heritable error (germline mutation) rates. Does the same theory also explain variation in phenotypic error rates and in abundance of error mitigation mechanisms? Translational read-through provides a model to investigate both issues as it is common, mostly nonadaptive, and has good proxy for rate (TAA being the least leaky stop codon) and potential error mitigation via “fail-safe” 3′ additional stop codons (ASCs). Prior theory of translational read-through has suggested that when population sizes are high, weak selection for local mitigation can be effective thus predicting a positive correlation between ASC enrichment and Ne. Contra to prediction, we find that ASC enrichment is not correlated with Ne. ASC enrichment, although highly phylogenetically patchy, is, however, more common both in unicellular species and in genes expressed in unicellular modes in multicellular species. By contrast, Ne does positively correlate with TAA enrichment. These results imply that local phenotypic error rates, not local mitigation rates, are consistent with a drift barrier/nearly neutral model.

Enhancing localization accuracy of collaborative cognitive radio users by internal noise mitigation

Location information of mobile primary users is one of the essential requirements for an underlay cognitive radio user to utilize the licensed spectrum efficiently. The performance of various location-based applications such as global navigation satellite system, device to device communication in dense urban 5G network also depends on the localization accuracy. In this paper, a collaborative localization scheme based on received signal strength has been proposed. The weighted centroid localization algorithm has been applied in the proposed network scenario to compute location coordinates of the mobile primary user. Since the channel noise effects are random and unavoidable, this paper has focused on the mitigation of the internal noise by designing a suitable reconfigurable FIR filter after the demodulator stage of a cognitive radio receiver circuit to improve precision of signal measurement during primary user localization. The localization error rate has come down to (1.3–1.62) % after internal noise mitigation. The enhancement in the localization accuracy improves the overall spectrum utilization efficiency and reduces the miss detection and false detection probabilities in the proposed underlay network.

Rough set based semi-supervised feature selection via ensemble selector

Similar to feature selection over completely labeled data, the aim of feature selection over partially labeled data (semi-supervised feature selection) is also to find a feature subset which satisfies the intended constraint. Nevertheless, two difficulties may emerge in the semi-supervised feature selection: (1) labels are incomplete since labeled and unlabeled samples coexist in data; (2) the explanation of the selected feature subset is not clear. Therefore, such two problems will be mainly addressed in our research. Firstly, the unlabeled samples can be predicted through various semi-supervised learning methods. Secondly, the Local Neighborhood Decision Error Rate is proposed to construct multiple fitness functions for evaluating the significance of the candidate feature. Such mechanism not only realizes the ensemble selector in the process of feature selection, but also the qualified feature subset will bring us lower decision errors. Immediately, a heuristic algorithm is re-designed to execute feature selection. Finally, through testing nine different ratios (10%, 20%, …, 90%) of labeled samples in data, the experimental results demonstrate that our approach is superior to previous researches, mainly because: (1) the qualified feature subset derived by our approach can provide better classification performance; (2) the lower time consumption is required in our process of feature selection.

Exploiting spatial audio cues for pilot navigation in degraded visual environments

Aviation mishaps resulting from degraded visual environments (DVEs) represent a significant loss in military personnel and aircraft every year. DVEs are considered any type of environmental condition (e.g., sand, snow, or fog) that visually obstructs the pilot and can cause spatial disorientation. The current study represents a tri-service effort exploring the implementation of spatial audio cueing techniques to aid pilot navigation in DVEs. Directional cueing (i.e., indicating the location of target waypoints) was achieved by spatializing an auditory stimulus using the SoundLab audio rendering package and convolving audio signals with (non-individualized) head-related transfer functions. Two spatial cue conditions were tested, either rendered dynamically in reference to the pilot’s head via head tracking or with respect to aircraft heading. Data were collected from pilots operating a full-motion UH-60 Black Hawk flight simulator at the U.S. Army Aeromedical Research Laboratory. Pilots performed multiple flight maneuvers, such as a “turn to target” localization task, a "side-step" maneuver positioning the aircraft over a stationary target, and an “approach to moving target” task. Performance was assessed by measures of localization error, completion time, and failure rate. Findings from this study provide information on sensory cueing display countermeasures for helicopter flight in DVEs.