Fingerprint Data Research Articles

Recent Progress of Advanced AIE Materials for Visualization of 3‐Level Latent Fingerprints

The 3‐level features of Latent fingerprints (LFPs) are pivotal in linking suspects with problematic or incomplete fingerprint data, constituting one of the most robust forms of evidence. Aggregation‐induced emission (AIE) materials, known for their heightened emissive properties in high aggregation states, provide a robust and powerful approach for developing techniques for 3‐level details of LFPs. So far, tremendous efforts have been devoted to solving high background fluorescence interference during the 3‐level LFPs visualization process. This review commences with an overview of 3‐level features and summarizes the interaction and mechanism of visualizing LFPs involving AIE materials and LFPs secretions. Moreover, it encompasses strategies to enhance the contrast and brightness of 3‐level LFPs images. We highlight the mechanism of AIE's physicochemical properties and their effects on the visualization of 3‐level LFPs. Additionally, we provide insights into potential challenges and opportunities in this emerging field.

BiTGNN: Prediction of drug–target interactions based on bidirectional transformer and graph neural network on heterogeneous graph

Drug–target interaction (DTI) is a widely explored topic in the field of bioinformatics and plays a pivotal role in drug discovery. However, the traditional bio-experimental process of drug–target interaction identification requires a large investment of time and labor. To address this challenge, graph neural network (GNN) approaches in deep learning are becoming a prominent trend in the field of DTI research, which is characterized by multimodal processing of data, feature learning and interpretability in DTI. Nevertheless, some methods are still limited by homogeneous graphs and single features. To address the problems, we mechanistically analyze graph convolutional neural networks (GCNs) and graph attentional neural networks (GATs) to propose a new model for the prediction of drug–target interactions using graph neural networks named BiTGNN [Bidirectional Transformer (Bi-Transformer)–graph neural network]. The method first establishes drug–target pairs through the pseudo-position specificity scoring matrix (PsePSSM) and drug fingerprint data, and constructs a heterogeneous network by utilizing the relationship between the drug and the target. Then, the computational extraction of drug and target attributes is performed using GCNs and GATs for the purpose of model information flow extension and graph information enhancement. We collect interaction data using the proposed Bi-Transformer architecture, in which we design a bidirectional cross-attention mechanism for calculating the effects of drug–target interactions for realistic biological interaction simulations. Finally, a feed-forward neural network is used to obtain the feature matrices of the drug and the target, and DTI prediction is performed by fusing the two feature matrices. The Enzyme, Ion Channel (IC), G Protein-coupled Receptor (GPCR) and Nuclear Receptor (NR) datasets are used in the experiments, and compared with several existing mainstream models, our model outperforms in Area Under the ROC Curve (AUC), Specificity, Accuracy and the metric Area Under the Precision–Recall Curve (AUPR).

On the security risk of pre-image attack on cancelable biometrics

Over the years, a number of biometric template protection schemes, often based on the notion of “cancelable biometrics”, have been proposed. An ideal cancelable biometric algorithm complies with four criteria: irreversibility, revocability, unlinkability, and performance preservation. Cancelable biometrics employs an irreversible but distance preserving transformation to convert the original biometric templates into protected templates. Matching in the transform domain can be accomplished due to the property of distance preservation. However, distance preservation also entails security issues, a point often overlooked in existing research. In this paper, we have conducted a comprehensive security analysis of distance preservation in cancelable biometrics for the first time. The analysis is based on a pre-image attack, which is launched to break the security of cancelable biometrics under Kerckhoffs’s assumption. Furthermore, we propose a general security analysis framework under the single and cross-transformation attacks, which also employs an information leakage estimation strategy based on mutual information as a complement. The experimental results performed on real face, iris, and fingerprint data demonstrate that the risks originating from the matching scores computed from the distance/similarity of two cancelable templates greatly compromise the security of cancelable biometric schemes, including the classic Biohashing, Index-of-max hashing, Non-linear multi-dimensional spectral hashing, Indexing-First-One hashing, Bloom Filter and Two-factor Protected Minutia Cylinder-Code. The security versus accuracy trade-off is discussed and recommendations for designing a biometric system secure against pre-image attacks are also proposed. The source code is available at github.com/biometricsecurity/CBrisks.

Fingerprint-Based Localization Enabled by Low-Rank Matrix Reconstruction in Intelligent Reflective Surface-Assisted Networks

The intelligent reflective surface (IRS) is a novel network node that consists of a large-scale passive reflective array to obtain a customized reflected wave direction by modulating the amplitude phase, which can be easily deployed to change the wireless signal propagation environment and enhance the communication performance under a non-line-of-sight (NLOS) environment, where location services cannot perform accurately. In this study, a low-rank matrix reconstruction-enabled fingerprint-based localization algorithm for IRS-assisted networks is proposed. Firstly, a 5G positioning system based on IRSs is constructed using multiple IRSs deployed to reflect signals. This enables the base station to overcome the influence of NLOS and receive the positioning signal of the point to be positioned. Then, the angular domain power expectation matrix of the received signal is extracted as a fingerprint to form a partial fingerprint database. Next, the complete fingerprint database is reconstructed using the low-rank matrix fitting algorithm, thereby considerably reducing the workload of building the fingerprint database. Finally, maximal ratio combining is used to increase the gap between the fingerprint data, and the Weighted K-Nearest Neighbor (WKNN) algorithm is used to match the fingerprint data and estimate the location of the points to be located. The simulation results demonstrate the feasibility of the proposed method to achieve sub-meter accuracy in an NLOS environment.

Construction of a DNA Fingerprint Map and a Core Collection of Platycladus orientalis

Platycladus orientalis is one of the main species used in afforestation projects in the arid mountains of north and northwest China, meaning that the species has high ecological and economic value. Studying its genetic diversity and obtaining a core germplasm base and genetic fingerprint data are important for the screening, development, and utilization of the species. This can provide the core materials for the preservation and evaluation and mining of germplasm resources and can provide superior gene resources for breeding programs. In this study, the genetic diversity among 104 P. orientalis germplasm resources was examined using simple sequence repeat (SSR) markers, and a core germplasm containing 31 accessions was constructed that represents the most genetic diversity of P. orientalis accessions. Each of 20 pairs of primers showed polymorphism, and 117 alleles were identified. The average number of alleles at each locus was six, and the mean effective allele number was 2.607. The average Shannon’s information index was 0.983, and the average polymorphism information content was 0.445. There is thus a significant amount of genetic variation within P. orientalis germplasm, yielding a rich genetic diversity. The constructed core germplasm accounted for 30% of the original germplasm. There was no significant difference in genetic diversity between the core germplasm and the original germplasm resources, indicating that the obtained core germplasm resources could fully represent the original germplasm. Using 17 SSR primers with high polymorphism, the DNA fingerprints of 104 P. orientalis germplasm resources were constructed. The results showed that 98 had specific DNA fingerprints. The results of this study provide a valuable basis for the collection, preservation, and utilization of P. orientalis germplasm resources, and the methods adopted in this study have important reference value for the construction of core germplasm of other perennial woody plants.

Forensic Fingerprint Analysis

Fingerprint evidence found at crime scenes provides vital impressions left when these skin secretions touch surfaces clues in serial criminal investigations. A fingerprint identification system employing deep machine learning and Convolutional Neural Networks (CNNs) could automate the analysis process. Images obtained from various physical and chemical crime scene investiga2tion techniques are entered into the database. However, partial latent prints lifted from scenes are often difficult to classify. The system operates in three phases: preprocessing fingerprint images, feature extraction, and matching. Preprocessing enhances image quality before feature extraction identifies distinctive minutiae points - ridge endings and bifurcations. False minutiae removal further refines the data. The preprocessed fingerprint data serves as input to train and test the CNN model. As the system persist due to the immutable individuality of fingerprint ridge arrangements [5]. While criminals attempt concealment, fingerprint traces stubbornly remain where other evidence would dissipate [6]. Without these durable biometric markers, crime scenes would often lack the critical traces needed to connect acts to perpetrators [7]. Latent prints lifted from crime scenes first undergo photographic documentation and chemical enhancement techniques in order to visualize trace details [8]. Computer analysis then further improves clarity, isolating minute identifying features known as minutiae [9]. Algorithmic extraction of differentiating traits classifies new latent prints, it continuously incorporates the prints enables training of automated comparison systems using along with confirmed suspect identity matches to improve accuracy. Automated classification and matching facilitate identification. The approach scales as the database grows in size without proportionate growth in human effort. Rapid fingerprint evidence analysis accelerates investigations, potentially solving more crimes by linking serial cases through a central digital repository. I aimed to restate the key technical ideas and flow using alternative vocabulary and phrasing while preserving semantic meaning. Please let me know if you need any clarification or have additional requirements for rephrasing the passage.

Design of Fingerprint-Based Gender Clustering Using Fuzzy C-Means Algorithm

Biometric systems, with fingerprint recognition as a cornerstone, play a crucial role in identity verification and access control. This paper introduces an innovative approach to gender clustering based on fingerprint data, leveraging the Fuzzy C-Means (FCM) algorithm. The proposed design aims to enhance the precision of gender classification by incorporating the inherent uncertainty in fingerprint features. Through the integration of FCM, which allows soft assignment of fingerprints to gender clusters, the system achieves a nuanced and adaptable classification. The study meticulously explores the design considerations, including the selection of features, data preprocessing, and the configuration of FCM parameters. Additionally, the paper discusses the experimental results, demonstrating the effectiveness of the proposed method in accurately clustering fingerprint data according to gender. The research contributes to the evolving field of biometrics, offering a novel perspective on gender classification that embraces the complexity of fingerprint patterns. The outcomes provide valuable insights for the development of reliable and versatile biometric systems, with potential applications in security, forensics, and personalized identification

Enhancing Indoor Localization With Semi-Crowdsourced Fingerprinting and GAN-Based Data Augmentation

Enhancing Indoor Localization With Semi-Crowdsourced Fingerprinting and GAN-Based Data Augmentation

Indoor positioning fingerprint database construction based on CSA-DBSCAN and RCVAE-GAN

With the increasing size of buildings, in order to achieve high-precision indoor positioning services, it is a challenging task to build an offline fingerprint database with high quality, high density and less manpower and material consumption. Aiming to solve the problem of low-quality WiFi indoor positioning fingerprint inventory constructed by traditional methods, which affects positioning accuracy and incurs high costs, this paper proposes a method for indoor positioning fingerprint database construction based on Crow Search Algorithm Optimizes Density Clustering (CSA-DBSCAN) and Regressor Conditional VAE Generative Adversarial Network (RCVAE-GAN). Collecting only a tiny amount of sparse reference point position coordinates and RSS data makes it possible to construct a high-quality WiFi indoor positioning fingerprint database. Firstly, the method utilizes the density clustering method based on Crow Search Algorithm Optimization (CSA-DBSCAN) to process RSS data collected from the reference point. This helps minimize the impact of abnormal RSS data on creating the fingerprint database. Secondly, the RCVAE-GAN depth generation model was developed. The model consists of an encoder E, a generator G, a discriminator D, and a regressor R. After constructing the model, the data with abnormal RSS will be removed and input into the model for pre-training and joint training, resulting in a high-quality deep-generation model. Finally, a high-quality and high-density fingerprint database is constructed by combining the collected reference points with fingerprint data generated by the depth generation model. Experimental results show that the proposed method reduces the root mean square error (RMSE) deviation of the generated fingerprint data by 38% and 12% respectively, compared to the RBF interpolation method and the CVAE-GAN method in the same experimental scenario. The constructed fingerprint database is used for positioning, improving positioning accuracy by 70% and 65% respectively. The method described in this paper can construct a high-quality fingerprint database, effectively improving the efficiency of fingerprint database construction and reducing the costs associated with labor and time.

Data augmentation-based enhanced fingerprint recognition using deep convolutional generative adversarial network and diffusion models

The progress of fingerprint recognition applications encounters substantial hurdles due to privacy and security concerns, leading to limited fingerprint data availability and stringent data quality requirements. This article endeavors to tackle the challenges of data scarcity and data quality in fingerprint recognition by implementing data augmentation techniques. Specifically, this research employed two state-of-the-art generative models in the domain of deep learning, namely Deep Convolutional Generative Adversarial Network (DCGAN) and the Diffusion model, for fingerprint data augmentation. Generative Adversarial Network (GAN), as a popular generative model, effectively captures the features of sample images and learns the diversity of the sample images, thereby generating realistic and diverse images. DCGAN, as a variant model of traditional GAN, inherits the advantages of GAN while alleviating issues such as blurry images and mode collapse, resulting in improved performance. On the other hand, Diffusion, as one of the most popular generative models in recent years, exhibits outstanding image generation capabilities and surpasses traditional GAN in some image generation tasks. The experimental results demonstrate that both DCGAN and Diffusion can generate clear, high-quality fingerprint images, fulfilling the requirements of fingerprint data augmentation. Furthermore, through the comparison between DCGAN and Diffusion, it is concluded that the quality of fingerprint images generated by DCGAN is superior to the results of Diffusion, and DCGAN exhibits higher efficiency in both training and generating images compared to Diffusion.

Blind-Touch: Homomorphic Encryption-Based Distributed Neural Network Inference for Privacy-Preserving Fingerprint Authentication

Fingerprint authentication is a popular security mechanism for smartphones and laptops. However, its adoption in web and cloud environments has been limited due to privacy concerns over storing and processing biometric data on servers. This paper introduces Blind-Touch, a novel machine learning-based fingerprint authentication system leveraging homomorphic encryption to address these privacy concerns. Homomorphic encryption allows computations on encrypted data without decrypting. Thus, Blind-Touch can keep fingerprint data encrypted on the server while performing machine learning operations. Blind-Touch combines three strategies to efficiently utilize homomorphic encryption in machine learning: (1) It optimizes the feature vector for a distributed architecture, processing the first fully connected layer (FC-16) in plaintext on the client side and the subsequent layer (FC-1) post-encryption on the server, thereby minimizing encrypted computations; (2) It employs a homomorphic encryption-compatible data compression technique capable of handling 8,192 authentication results concurrently; and (3) It utilizes a clustered server architecture to simultaneously process authentication results, thereby enhancing scalability with increasing user numbers. Blind-Touch achieves high accuracy on two benchmark fingerprint datasets, with a 93.6% F1- score for the PolyU dataset and a 98.2% F1-score for the SOKOTO dataset. Moreover, Blind-Touch can match a fingerprint among 5,000 in about 0.65 seconds. With its privacy-focused design, high accuracy, and efficiency, Blind-Touch is a promising alternative to conventional fingerprint authentication for web and cloud applications.

Fingerprint Based Driving License Management System

The "Fingerprint-Based Driving License Detector" is an innovative system designed to enhance the security and authenticity of driving licenses through the integration of biometric technology. This system leverages fingerprint recognition as a robust method to verify the identity of drivers, aiming to reduce instances of license fraud and unauthorized use. The proposed system consists of a comprehensive framework that involves capturing and storing the fingerprint data of individuals during the driving license issuance process. This biometric data is then securely linked to the respective driving license records in a centralized database. During routine traffic stops or license verification processes, law enforcement authorities can use fingerprint scanners to quickly and accurately verify the identity of the license holder. The implementation of this system offers several advantages, including heightened security, reduced instances of identity theft, and a more streamlined and efficient license verification process. Additionally, the integration of fingerprint-based authentication enhances the overall trustworthiness of the driving license system, fostering a safer and more reliable environment on the roads. Keywords: Fingerprint Recognition, Driving License Authentication, Biometric Technology, Identity Verification.

IoT Based Smart Attendance Management System

Abstract: This research work has application for attendance system of employer's and students in general. The system will facilitate institutions! organization to make attendance individual in time along with data information thumb impression will be taken as a signature for the system entry. Main design and challenge in this system is the design of database architecture and its business logic. I. AIMS AND OBJECTIVE The aim of this system is to implement in C#.net set of reliable techniques for fingerprint image enhancement and minutiae extraction. The performance of these techniques will be evaluated on a fingerprint data set. In combination with these development techniques, statistical experiments can then be performed on the fingerprint data set. The results from these experiments can be used to help us better understand what is involved in determining the statistical uniqueness of fingerprint minutiae. The main aim that this system would test whether attendance by fingerprint is enough for identification. It is expected that the work in this system will reach the stage of being able to fully test hypothesis. II. BACKGROUND/CONTEXT Fingerprints are the oldest form of biometric identification. Modem fingerprint-based identification is used in forensic science, and in biometric systems such as civilian identification devices. Keywords: the fingerprint data, statistical uniqueness of fingerprint minutiae.

SecureSense: Enhancing Person Verification through Multimodal Biometrics for Robust Authentication

Biometrics provide enhanced security and convenience compared to conventional methods of individual authentication. A more robust and effective method of individual authentication has emerged due to recent advancements in multimodal biometrics. Unimodal systems offer lower security and lack the robustness found in multimodal biometric systems. The research paper introduces a novel approach, employing multiple biometric modalities, including face, fingerprint, and iris, to authenticate users in a multimodal biometric system. The paper proposes the ”Secure Sense” framework, which combines multiple biometric modalities to improve person verification accuracy. The proposed system utilizes both web-based and real-time datasets. For the web-based dataset, we employed the Chicago Face dataset for facial data, the MMU1 dataset for iris data, and the SOCOfing dataset for fingerprint data. In real-time data collection, facial data is captured using a Zebronics Zeb-Gem webcam, fingerprint data is obtained using the Mantra MFS scanner, and iris data is collected using the Mantra MIS scanner. In the envisioned system, we introduce an innovative approach that employs a decision-level fusion technique across three unique biometric modalities, resulting in an impressive accuracy rate of approximately 93% across all modalities.

Cloud Security System for ECG Transmission and Monitoring Based on Chaotic Logistic Maps

Biomedical data or information must be transmitted securely via the internet for smart healthcare. The Electrocardiogram (ECG) signal is amongst the most essential clinical signals which must be delivered to hospital facilities. Prime focus of this research is on the encryption of ECG for secure transmission. Chaos theory is used for the development of deterministic nonlinear systems, that can be used to create random numbers for the Chaotic Logistic Map (CLM) based encryption. This study describes a cryptographic algorithm for encrypting ECG signals that uses a mix of the CLM and fingerprint data. The common factor between the patient section and monitoring section is the operation on sample data points of ECG. The choice of proper encryption and decryption theme can save more amount of time and is invulnerable both to noise-based attacks and hacking instances. The proposed framework is implemented on Dropbox based cloud storage and access is possible from any given locations. Simulation tests are used to assess the system performance in terms of Structural Similarity Index Matrix (SSIM), Histogram, Spectral Distortion (SD), Correlation and Log-Likelihood Ratio (LLR). The incorporation of complex layers of CLM encryption increases security.

Electrochemical fingerprinting and phylogenetic analysis of Inula species

This study presents a groundbreaking approach in the chemotaxonomic classification of Inula species through electrochemical fingerprinting and multivariate data analysis. Focusing on 14 different Inula species, the research utilized differential pulse voltammetry to analyze leaf extracts in varying pH conditions (acetate pH 4.5, phosphate pH 7.0, and Tris pH 9.0). The electrochemical profiles generated were distinctive and informative, revealing specific oxidation peaks associated with phytochemical compounds. Principal component analysis (PCA) efficiently captured 91.0 % of the variance in these profiles, effectively distinguishing between species. Hierarchical cluster analysis further corroborated these findings, accurately classifying each species into distinct clusters. The method proved exceptionally precise in identifying unknown Inula samples, achieving a 100 % success rate when matched against a reference library. This approach significantly enhances the rapid identification and quality assurance of medicinal herbs, offering a simpler, faster alternative to traditional chemotaxonomic methods.

A channel state information and geomagnetic fused fingerprint localisation algorithm based on multi‐input convolutional neural network

AbstractNumerous applications require indoor localisation, and one of the current research areas is how to leverage low‐cost ubiquitous signals for indoor localisation. This research designs a multi‐input convolutional neural network (Multi‐CNN) localisation approach to combine natural geomagnetic signals and universal 5G communication signals. To create the location fingerprint data, the geomagnetic three‐component data and channel state information (CSI) must first undergo independent preprocessing. Subsequently, the rebuilt CSI amplitude and geomagnetic intensity are employed for separate offline training to efficiently extract the corresponding data features. Lastly, Multi‐CNN is used to estimate the user's location online. The localisation outcomes for the conference room and hall demonstrate that the Multi‐CNN algorithm can achieve average localisation accuracies of 1.41 and 2.66 m, respectively. These are higher than the single‐input CNN algorithms by 21% and 15%, and higher than backpropagation network (BPNN) algorithm by 24% and 17%, and higher than the weighted K‐nearest neighbour algorithm by 34% and 28%. The Multi‐CNN‐based localisation approach successfully fuses the diverse data, potentially satisfying most indoor localisation applications.

Machine learning-based fluorescence sensor array: Accurate discrimination, quantitative assay of phenothiazine drugs via versatile DNA probes

Phenothiazine drugs are widely used to treat psychotic diseases in humans. The phenothiazine ligand enables unique interaction between the drugs and DNA double helix. We discovered that it was impossible to select aptamer to selectively bind with phenothiazine drug. In this study, an alternative fluorescence sensor array was first developed to accurately discriminate four typical phenothiazine drugs based on machine learning. As the eight sensor elements, versatile DNA probes were designed based on different oligonucleotides, two unique fluorescence dyes, and diverse buffer solutions. The fingerprint data can offer the fluorescence response patterns against each phenothiazine drug. Linear discriminant analysis (LDA) can discriminate single one or mixture samples of phenothiazine drugs with 100% accuracy. Besides, one neural network model showed a good linear relationship between predicted and actual concentrations to quantitatively assay specific phenothiazine drugs. The proposed fluorescence sensor array presents a new way to accurately discriminate phenothiazine drugs in pharmacy or biology field.

Bioactivity assay of Arundina graminifolia (D.Don) Hochr. extracts from diverse plant parts in Thailand: An assay-based investigation

This research involved surveying and collecting 16 samples of Arundina graminifolia from 8 different subpopulation areas. The main objectives were to analyze the preliminary phytochemical fingerprints and biological activity of the crude extracts obtained from various parts of the plant (roots, rhizomes, stems, and leaves). The findings indicated that rhizome extracts generally yielded a higher percentage of crude extract compared to the dry plant weight in comparison to other plant parts. Moreover, the Thin layer chromatography (TLC) fingerprint data revealed distinct compositions for each part of the plant, with rhizomes exhibiting more prevalent bands of compounds than other parts. Regarding antioxidant activity, the root and rhizome crude extracts from various populations displayed stronger inhibitory activity against DPPH, ABTS, and FRAP methods compared to stems and leaves. High total phenolic content was also found to effectively inhibit free radicals. The lipoxygenase inhibition test, which serves as an in vitro anti-inflammatory activity evaluation, demonstrated that most root extracts exhibited higher lipoxygenase inhibitory activity than the rhizome extracts at a concentration of 0.1 mg/mL. The antibacterial activity demonstrated that rhizome extracts from different regions exerted lower MIC and MBC values against all tested bacteria compared to the root extracts. The findings offer valuable information for selecting specific populations of A. graminifolia as potential sources of bioactive compounds for future nutraceutical applications.

Automatic Fingerprint Data Labeling Using WiFi Signal and Smartphone Camera for Indoor Positioning

WiFi fingerprinting has been one of the most practical approaches for implementing an indoor positioning system. However, the need to measure location labels for fingerprint data has hindered the deployment of WiFi fingerprint‐based positioning systems. To reduce the cost of location labeling, several methods for automatically labeling locations or bypassing location labeling have been proposed. However, these methods still need to measure location labels for partial fingerprint data, or the estimated location labels are inaccurate. In this paper, we propose Heimdall, an automatic fingerprint data labeling method using a smartphone camera and WiFi signal for an indoor positioning system. Since Heimdall utilizes camera geometry for accurate automatic labeling, it aims to find the location labels of unlabeled fingerprint data composed of WiFi received signal strengths (RSSs) and photos collected using smartphones in multiple reference points (RPs). Using structure from motion (SfM) with all photos in the unlabeled fingerprint dataset, the location and orientation of the cameras can be recovered on an arbitrary world coordinate system. However, the world coordinate system derived by SfM is warped. In other words, it is different from the real‐world coordinate system where we express the location labels since SfM has similarity ambiguity, including scale, rotation, and translation ambiguity. Heimdall finds the location labels by estimating and applying an unwarping transformation that removes those ambiguities. We use two types of geometric constraints for estimating the unwarping transformation. First, several geometric entities in the warped‐world coordinates and real‐world coordinates are extracted from the photos and prior information about the indoor layout. The unwarping transformation transforms the geometric entities in warped coordinates to those in real‐world coordinates. Second, we utilize the log‐distance pathloss model with RSSs to derive the constraint about distances from the location label to the access points. We construct the optimization problem subject to those constraints to estimate the unwarping transformation. To evaluate the performance of Heimdall, we performed several experiments. Heimdall yields a mean location labeling error of 0.12 m and a standard deviation of location labeling error of 0.06 m for the best case in the experiment. These results demonstrate that a fingerprint‐based indoor positioning system can use the location labels estimated by Heimdall without performance degradation.