DBSCAN Research Articles

Apple tree architectural trait phenotyping with organ-level instance segmentation from point cloud

Three-dimensional (3D) plant phenotyping techniques measure organ-level traits effectively and provide detailed plant growth information to breeders. In apple tree breeding, architectural traits can determine photosynthesis efficiency and characterize the developmental stages of trees. The overall goal of this study was to develop a deep learning-based organ-level instance segmentation method to quantify the 3D architectural traits of apple trees. This study utilized PointNeXt for the semantic segmentation of apple tree point clouds, classifying them into trunks and branches, and benchmarked its performance against several competitive models, including PointNet, PointNet++, and Point Transformer V2 (PTv2). A cylinder-based constraint method was introduced to refine the semantic segmentation results. Next, the branches were identified with the density-based spatial clustering of applications with noise (DBSCAN) algorithm. The type of 3D skeleton vertices determined whether a cluster represented a single branch or multiple branches. If multiple, a graph-based technique further separated them. This study also directly applied the instance segmentation model SoftGroup++ to the apple tree point clouds and analyzed the segmentation results on the apple tree dataset. Finally, seven architectural traits of apple trees were extracted, including height, volume, and crown width of the tree, as well as height and diameter for the trunk, and length and count for the branches. The experimental results showed that the post-processed mIoU values for PointNet, PointNet++, PTv2, and PointNeXt were 0.8495, 0.8535, 0.9500, and 0.9481, respectively. The final instance segmentation results based on SoftGroup++ and PointNeXt achieved mAP_50 of 0.815 and 0.842, respectively. For traits such as tree height, trunk length and diameter, branch length, and branch count, the method based on PointNeXt achieved R2 values of 0.987, 0.788, 0.877, 0.796, and 0.934, with mean absolute percentage errors of 0.86 %, 2.17 %, 5.93 %, 10.24 %, and 13.55 %, respectively. The segmentation results of PTv2 and SoftGroup++ were also used to extract the phenotypic traits of apple trees, achieving results comparable to those of PointNeXt. The proposed method demonstrates a cost-effective and accurate approach for extracting the architectural traits of apple trees, which will benefit apple breeding programs as well as the precision management of apple orchards.

Geospatial and econometric approaches or older driver safety: Analysis of crash injury severity of regional highways.

This study tried to focus on the older drivers' group and explore the impact factors of injury severity involving older drivers from geo-spatial analysis. To reach the goal, a spatial analysis was proposed employing geographic information systems (GIS) with a case study application to two counties in Nevada. First, crash clusters were explored using Density-Based Spatial Clustering of Applications with Noise (DBSCAN) approach to investigate the spatial crash pattern for older drivers, and determine high risk locations of injury severity. Next, Bayesian spatial binary probit model was presented in order to determine the significant impact factors of injury severity involving older drivers. It was found that at-fault driver condition and vehicle condition, not-at-fault vehicle action and road factors were significant factors for injury severity of older drivers. Results revealed that DBSCAN provides a solid option for hotspot identification of injury severity and Bayesian spatial binary probit model addresses the factor determinants spatially. The GIS-based spatial analysis can benefit more reliable older driver-concentrated evaluation and injury severity analysis.

Leveraging machine learning for enhanced reservoir permeability estimation in geothermal hotspots: a case study of the Williston Basin

Geothermal energy is a large, renewable, and clean source of energy from the earth in the form of heat. Exploring the deeper layers of the Williston Basin has revealed favorable reservoir temperatures, particularly in the western areas where high heat flows are prevalent. The quality of a geothermal hotspot hinges on the reservoir quality index (RQI), which is determined by the accuracy of calculating the field reservoir permeability. The primary goal of this study is to apply machine learning techniques to accurately calculate the field permeability, which is important for optimizing the RQI. To enhance accuracy, we initially applied various clustering algorithms, including the density-based spatial clustering of applications with noise (DBSCAN), K-means, K-median, and hierarchical clustering methods, to delineate hydraulic flow units (HFU) within the reservoir using porosity, permeability and water saturation core data. Subsequently, regression models including supervised ML regression methods such as neural networks, support vector machine (SVM) regression, Gaussian process regression (GPR), ensemble regression, linear regression, and decision trees were employed for each flow unit to establish correlations and calculate field permeability with each of these models validated using cross-validation. In comparison to the other clustering methods, the hierarchical clustering method showed the best performance by showing a strong correlation between the actual and predicted permeability values. Overall, the SVM and GPR regression methods were observed to show consistent results with the training and testing datasets, with the SVM regression technique yielding higher R-squared values through regression across the different clustering techniques. In addition, cross-plots were employed to successfully delineate the Red River formation into distinct regions, aiding in the definition of formation lithology and the estimation of field water saturation. Our study showcases an integrated approach to predicting reservoir permeability, considering limited core data. ML emerges as an effective tool for characterizing the Red River formation as a geothermal hotspot in North Dakota, showcasing the potential for sustainable energy exploration and utilization which reduces the reliance on extensive coring in order to enhance geothermal exploration accuracy.

Revolutionizing population sparsity assessment: machine learning–powered solutions for multi-objective evolutionary algorithms

Decomposed multi-objective evolutionary algorithms have recently gained attention in research, with population sparsity often evaluated through Euclidean distance. However, individuals with high sparsity tend to be located along the edges of the Pareto front, whereas those with low sparsity cluster towards the centre. This article introduces a more accurate method for assessing individual sparsity in the objective space using the density-based spatial clustering of applications with noise (DBSCAN) algorithm. The contributions of this work include (1) identifying the limitations of using Euclidean distance for sparsity measurement, (2) mitigating DBSCAN sensitivity to input parameters through adaptive adjustment via a genetic algorithm and (3) integrating DBSCAN with multi-objective algorithms to address the limitations of Euclidean distance by leveraging core and boundary points. Experimental results on three benchmark test problems and an engineering application involving mechanical bearings highlight the proposed algorithm's strong performance and competitiveness.

Multi-layer access control for cloud data using improved DBSCAN, AES, homomorphic encryption, and RMAAC for text, image, and video

With the growing demand for cloud storage solutions that can handle diverse data types such as text, images, and videos, ensuring robust access control and security becomes important. This paper proposes a novel multi-layer access control framework for cloud environments, incorporating advanced Clustering Filtering Techniques with an Improved DBSCAN (Density-Based Spatial Clustering of Applications with Noise) algorithm to enhance search efficiency across multiple data layers. This clustering approach enables quick and accurate retrieval of text, image, and video content by efficiently organizing data based on similarity. To ensure data privacy and security, employs a hybrid encryption approach, combining Advanced Encryption Standard (AES) for data at rest and Homomorphic Encryption (HE) for data in use, allowing secure data manipulation without compromising confidentiality. The access control mechanism is further strengthened by introducing a Role-based Multi-Attribute Access Control (RMAAC) model, which grants permissions based on a user’s role, attributes, and the sensitivity level of the data being accessed. This fine-grained control restricts unauthorized access while supporting flexible policies for different data types. Simulation results demonstrate that the proposed framework significantly improves data retrieval speed, security, and clustering performance, making it an effective solution for cloud storage systems handling diverse media formats.

Rapid Early Screening for Lymphedema Using Kinect

ABSTRACTBreast cancer related lymphedema (BCRL) is the swelling that generally occurs in the arms and is caused by the removal of or damage to lymph nodes as a part of invasive cancer treatment. Treating it at the earliest possible stage is the best way to manage the condition and prevent the pain, recurrent infection, reduced mobility, and impaired function. Current approaches for lymphedema detection include physical examination with tape measurement, lymphoscintigraphy, and magnetic resonance lymphangiography. The tape measurement method requires high manual involvement and lacks standardization, and the imaging modalities are expensive, time‐consuming and involve the injection of a contrast agent. To overcome these challenges, we built and validated a noncontact volumetric measurement system called rapid early screening for lymphedema (RESLy) consisting of (a) noninvasive Kinect infrared sensor‐based imaging that captures and builds a 3D reconstructed model of the body, (b) an automated segmentation process for extracting the region of interest (ROI), and (c) the volumetric computation of lymphedema. By employing density‐based spatial clustering of applications with noise (DBSCAN), which is a density‐based unsupervised learning algorithm, RESLy automatically segments out limbs from 3D maps, thereby streamlining automated measurements to be conducted quickly. The in‐lab calibration, testing, validation, and clinical deployment of RESLy among twelve patients in a tertiary cancer care department demonstrate that it is able to accurately identify limb volume differences with the least standard error of measurement, as well as identify lymphedema stages satisfactorily.

An Identification and Localization Method for 3D Workpiece Welds Based on the DBSCAN Point Cloud Clustering Algorithm

With the development of robotic welding automation, there is a strong interest in welding seam identification and localization methods with high accuracy, real-time performance, and robustness. This paper proposed a 3D workpiece weld identification and localization method based on DBSCAN (density-based spatial clustering of applications with noise) to realize stable feature extraction for multiple joint types. Firstly, this method employs combinatorial filtering to effectively eliminate non-target point clouds, including outliers and installation platform point clouds, which can minimize the computational load. Secondly, DBSCAN is used to classify workpiece point clouds into different clusters, which can be used for point cloud segmentation of flat workpieces and curved workpieces. Thirdly, the edge detection and feature extraction methods are used to obtain joint gap and weld feature points while combining the information of point clouds for different types of welds. Finally, based on the identification and localization of the welds, welding path planning and attitude planning are implemented. Experimentation results indicated that the proposed method exhibits robustness across various types of welded joints, including butt joints with straight seams, butt joints with curved seams, butt joints with curved workpieces, and lap joints. Meanwhile, the average error of joint gap detection was 0.11 mm and the processing time of a 90 mm straight-seam butt joint is 701.12 ms.

Early Fault Diagnosis and Prediction of Marine Large-Capacity Batteries Based on Real Data

The inconsistency of battery voltages in all-electric ships is a significant issue for electric vehicle battery systems, leading to numerous safety concerns during vessel operation. Therefore, timely fault diagnosis and accurate fault prediction are crucial for the safe operation of ships. This study examines the fault alarm system of marine battery management systems in conjunction with the unique operating conditions of ships, focusing on the system’s latency. To facilitate prompt fault detection, a fault diagnosis method based on the Density-Based Spatial Clustering of Applications with Noise (DBSCAN) algorithm is proposed, utilizing the voltage data of battery clusters. Results indicate that the DBSCAN clustering algorithm demonstrates superior effectiveness and accuracy in identifying irregular battery clusters. Furthermore, the fault prediction method based on the iTransformer model is introduced to forecast variations in battery cluster voltages. Experimental findings suggest that this model can effectively predict consistency faults and over-/under-voltage conditions based on battery cluster voltage values and corresponding fault thresholds.

Multi-scale offshore wind farm site selection decision framework based on GIS, MCDM and meta-heuristic algorithm

Offshore wind energy has emerged as a significant driving force to establish a sustainable energy system. Nevertheless, the field of wind farm site selection faces challenges regarding the lack of coherent scale of site selection and incomplete consideration of methodologies. To address these issues, this study proposes a multi-scale framework and methodology, which combines Geographic Information System (GIS), Multi-Criteria Decision Making (MCDM), and meta-heuristic algorithms. The goal of this study is to determine the optimal scheme, its location and boundary, by integrating large, small, and micro-scale site selection. Within this framework, a combined weighting method based on Group Intuitionistic Fuzzy Analytic Hierarchy Process (GIAHP) and the Method based on the Removal Effects of Criteria (MEREC) is proposed to calculate the criteria weights. Additionally, the improved ORESTE method based on Cumulative Prospect Theory (CPT) is employed to rank the alternatives. Finally, the improved Variable Neighborhood Search (VNS) and Density-Based Spatial Clustering of Applications with Noise (DBSCAN) algorithms are implemented to design the offshore wind farm and determine its location and boundary. The proposed framework is then applied in the Shandong sea area in China. The results, obtained through sensitivity analysis and comparative analysis, can serve as a foundation for decision makers.

Real-Time Radar Classification Based on Software-Defined Radio Platforms: Enhancing Processing Speed and Accuracy with Graphics Processing Unit Acceleration.

This paper presents a comprehensive evaluation of real-time radar classification using software-defined radio (SDR) platforms. The transition from analog to digital technologies, facilitated by SDR, has revolutionized radio systems, offering unprecedented flexibility and reconfigurability through software-based operations. This advancement complements the role of radar signal parameters, encapsulated in the pulse description words (PDWs), which play a pivotal role in electronic support measure (ESM) systems, enabling the detection and classification of threat radars. This study proposes an SDR-based radar classification system that achieves real-time operation with enhanced processing speed. Employing the Density-Based Spatial Clustering of Applications with Noise (DBSCAN) algorithm as a robust classifier, the system harnesses Graphical Processing Unit (GPU) parallelization for efficient radio frequency (RF) parameter extraction. The experimental results highlight the efficiency of this approach, demonstrating a notable improvement in processing speed while operating at a sampling rate of up to 200 MSps and achieving an accuracy of 89.7% for real-time radar classification.

Застосування системи тестового опитування на основі кластерного аналізу та машинного навчання в задачах профвідбору фахівців

The research aims to develop a test survey for the effective selection of specialists in the field of IT, utilizing modern machine learning methods, particularly cluster analysis with the k-means algorithm. Due to limited access to existing testing platforms, which are typically available only to large companies on a paid basis, a decision was made to create an alternative web application. This application will serve as an accessible tool for a wider range of users and will automate the evaluation of candidates' qualifications. The study involves designing a test survey specifically for recruiters in the IT field. Currently, similar tests are provided by the government but are usually accessible to companies only through subscriptions. To address this limitation, the alternative service—a web application—was proposed. The web application will leverage machine learning techniques, specifically the k-means clustering algorithm, to analyze user test results. A key feature of this research is the application of cluster analysis to group users based on their professional skills, cognitive abilities, and psychological characteristics. In addition to the k-means algorithm, other clustering methods such as hierarchical clustering and DBSCAN (Density-Based Spatial Clustering of Applications with Noise) were considered and tested to ensure robustness in grouping users. The combination of these methods enables both partitioning the data into clusters with predefined numbers of groups (via k-means) and identifying clusters with varying densities and shapes (via DBSCAN). Meanwhile, hierarchical clustering provides insights into relationships between data points at different levels of granularity. This approach allows for a more accurate assessment of candidates' suitability for employers’ requirements and facilitates better data organization for further analysis. The study highlights the importance of cluster analysis in situations where there is no prior hypothesis about the data structure, making it a versatile tool for data classification. Beyond the technical aspects, the research explores the potential of using adaptive tests that adjust the difficulty level in real-time based on the user’s responses. This enhances the accuracy of the assessment and minimizes the influence of subjective factors during the selection process. Furthermore, the study examines the potential for analyzing candidates’ behavioral and emotional characteristics, such as stress tolerance and communication skills, which are crucial for effective teamwork. The research confirmed the hypothesis that the testing challenge can be addressed by creating a web application capable of analyzing users' responses and providing detailed results. Based on these results, participants can evaluate their professional suitability for the IT field. Future developments may include the addition of new test categories and features if the system demonstrates its scalability and adaptability.

Research on flight intention recognition of UAVs-swarm

Abstract Most existing threat level assessments for aerial targets rely on numerical analysis and typically address only single or a few incoming targets without incorporating intention recognition. Such methods are inadequate for anti-UAV(Unmanned aerial vehicle) tasks involving large numbers of flight targets. To accurately and efficiently identify the flight intentions of UAVs-swarm, this paper proposes a method based on formation recognition and trajectory prediction. Initially, the trajectories of UAVs are obtained and clustered using the DBSCAN (Density-Based Spatial Clustering of Applications with Noise) algorithm. For each cluster, a Bayesian classifier is employed to recognize its flight formation. Subsequently, a minimum enclosing sphere is established for each cluster, and trajectory fusion and prediction are conducted based on the sphere’s center. Finally, a flight intention recognition model is constructed. The results demonstrate that this method effectively infers the flight intentions of each UAVs-cluster, providing a robust basis for the threat level assessment in anti-UAVs-swarm tasks.

PRODIGE – envelope to disk with NOEMA

Context. The formation of stars has been subject to extensive studies in the past decades on scales from molecular clouds to proto-planetary disks. It is still not fully understood how the surrounding material in a protostellar system, which often shows asymmetric structures with complex kinematic properties, feeds the central protostar(s) and their disk(s). Aims. We study the spatial morphology and kinematic properties of the molecular gas surrounding the IRS3A and IRS3B protostellar systems in the L1448N region located in the Perseus molecular cloud. Methods. We present 1 mm Northern Extended Millimeter Array (NOEMA) observations of the large program PROtostars & DIsks: Global Evolution (PRODIGE). We analyzed the kinematic properties of molecular lines. Because the spectral profiles are complex, the lines were fit with up to three Gaussian velocity components. The clustering algorithm called density-based spatial clustering of applications with noise (DBSCAN) was used to disentangle the velocity components in the underlying physical structure. Results. We discover an extended gas bridge (≈3000 au) surrounding both the IRS3A and IRS3B systems in six molecular line tracers (C18O, SO, DCN, H2CO, HC3N, and CH3OH). This gas bridge is oriented in the northeast-southwest direction and shows clear velocity gradients on the order of 100 km s−1 pc−1 toward the IRS3A system. We find that the observed velocity profile is consistent with analytical streamline models of gravitational infall toward IRS3A. The high-velocity C18O (2-1) emission toward IRS3A indicates a protostellar mass of ≈1.2 M⊙. Conclusions. While high angular resolution continuum data often show IRS3A and IRS3B in isolation, molecular gas observations reveal that these systems are still embedded within a large-scale mass reservoir, whose spatial morphology and velocity profiles are complex. The kinematic properties of the extended gas bridge are consistent with gravitational infall toward the protostar IRS3A.

Developing and Comparing Machine Learning Algorithms for Music Recommendation

The increasing prevalence of song skipping in music streaming applications negatively impacts user satisfaction and subscription retention. Dissatisfaction often arises when users encounter songs they actively dislike, highlighting a gap between user expectations and the value offered by these services. To address this, music recommendation algorithms were researched and developed. Initially, data collection is started. Data collection is through the Spotify application programming interface. This initiation step sets the stage for subsequent exploratory data analysis. Exploratory data analysis examined the collected data to plot a bar chart for total songs released over the years, plot a bar chart for the popularity of songs based on the year it is released, visualize word cloud on frequently mentioned music genres, chart count plot for explicit songs, and chart count plot for song modalities. Data preprocessing involved cleaning the data, handling missing values, and checking for null values to prepare the application of machine learning algorithms. Four machine learning algorithms were applied, k-means, mini-batch k-means, Gaussian mixture, and density-based spatial clustering of applications with noise (DBSCAN), to analyze musical features like rhythm, tempo, and other relevant music attributes. The results showed that the k-means outperforms all other algorithms evaluated regarding recommendation quality, as measured by the Calinski-Harabasz score. Based on the evaluation, the best machine learning will then be applied to identify similarities between songs and be used to generate music recommendation results.

Machine learning enabled uncertainty set for data-driven robust optimization

The way how the uncertainties are represented by sets plays a vital role in the performance of robust optimization (RO). This paper presents a novel approach leveraging machine learning (ML) techniques to construct data-driven uncertainty sets from historical uncertainty data for RO problems. The proposed method integrates Density-Based Spatial Clustering of Applications with Noise (DBSCAN), Gaussian Mixture Model (GMM), and Principle Component Analysis (PCA) systematically to eliminate the influence of uncertainty scenarios with low occurrence probability and generate a nonconvex uncertainty set that is a union of multiple basic subsets (box or ellipsoid) without sacrificing its computational tractability. In addition to presenting a comprehensive algorithm for uncertainty set development, this paper offers detailed guidelines for parameter tuning and performance analysis. By harnessing the well-established ML packages scikit-learn, a Python-based toolkit for implementing the proposed approach is also provided. Furthermore, a computationally efficient solution for a two-stage linear RO problem with the proposed data-driven uncertainty set is derived, alongside establishing a probabilistic guarantee of constraint satisfaction for out-of-sample uncertainties. Extensive numerical experiments, conducted on both synthetic and real-world datasets as well as an optimization-based control problem, are performed to demonstrate the efficacy of the proposed methodology.

Near-Earth stream decoherence revisited: the limits of orbital similarity

Orbital similarity measures, such as the D values, have been extensively used in meteor science to identify meteoroid streams and associate meteorite falls with near-Earth objects (NEOs). However, the chaotic nature of near-Earth space challenges the long-term reliability of these measures for stream identification, and the increasing size of our fireball, meteorite fall, and NEO databases make random associations more common. Despite this, many researchers erroneously continue to use orbital similarity beyond its inherent limits. We aim to assess the statistical significance of using orbital similarity measures for identifying streams of meteoroids or asteroids and explore the implications of chaotic dynamics on the long-term coherence of these streams. We employed a kernel density estimation (KDE) based method to evaluate the statistical significance of orbital similarities within different datasets. Additionally, we conducted a Lyapunov characteristic lifetime analysis and simulated 300 fictitious meteoroid streams to estimate the decoherence lifetimes in near-Earth space. The orbital similarity was determined using the D$_ SH $, D', and D$_ H $ orbital similarity discriminants. Clustering analysis relied on a density-based spatial clustering of applications with noise (DBSCAN) algorithm. Our analysis found no statistically significant streams within the meteorite fall, fireball, or USG impact datasets, with orbital similarities consistent with random associations. Conversely, 12 statistically significant clusters were identified within the NEO population, likely resulting from tidal disruption events. The Lyapunov lifetime analysis revealed short characteristic lifetimes (60–200 years) for orbits in near-Earth space, emphasizing the rapid divergence of initially similar orbits. Meteoroid stream decoherence lifetimes ranged from $10^4$ to $10^5$ years, aligning with previous studies and underscoring the transient nature of such streams. The rapid decoherence of meteoroid streams and the chaotic dynamics of near-Earth orbits suggest that no reported stream or NEO associations of meteorites or fireballs are statistically significant according to orbital discriminates. Many are likely coincidental rather than indicative of a true physical link. However, several statistically significant clusters found within the NEO population are consistent with a tidal disruption formation. This contrast and lack of statistically significant associations amongst the impact datasets is likely due to the fireball databases being 2 orders of magnitude smaller than the NEO database and the higher intrinsic uncertainties of fireball observation derived orbits.

Locating Strong Electromagnetic Pulses Recorded by a Single Satellite with Cluster Analysis and Worldwide Lightning Location Network Observations

The integration of satellite-borne and ground-based global lightning location networks offers a better perspective to study lightning processes and their evolutionary characteristics within thunderstorm clouds, thereby bolstering the predictive capabilities for severe weather phenomena. Currently, the satellite-borne network is in the preliminary testing phase with a single satellite. The geographic locations of single-satellite detection events primarily rely on synchronous information from coincident ground-based network events; this method is called synchronous locating (SCL). However, variations in detection-frequency bands and system capabilities prevent this method from accurately locating more than a mere 10% of events. To address this limitation, this paper introduces a cluster-analysis-based strategy, utilizing the observations from the Worldwide Lightning Location Network (WWLLN), termed the cluster analysis locating (CAL) method. The CAL method’s performance, influenced by the density-based spatial clustering of applications with noise (DBSCAN), the K-means, and the mean shift algorithms, is examined. Subsequently, an advanced version, mean shift denoised (MSDN)-CAL, is proposed, demonstrating marked improvements in location accuracy and reliability over the other CAL methods. The satellite-borne wideband electromagnetic pulse detector (WEMPD), orbiting at an altitude of approximately 500 km with a 97.5° inclination, captured 1061 strong electromagnetic pulses (EMPs). Among these, trans-ionospheric single pulses (TISPs) and trans-ionospheric pulse pairs (TIPPs) constituted 21.30% and 78.70%, respectively. Using the MSDN-CAL method successfully determines the geographic locations for 81.15% (861 out of 1061) of the events. This success rate represents an approximate eightfold enhancement over the SCL method. The arithmetic mean, geometric mean, and standard deviation of the two-dimensional range deviation of the locating results between the MSDN-CAL method versus the WWLLN-SCL (or the Guangdong-Hong Kong-Macao Lightning Location System (GHMLLS)-SCL) method are 51.06 (176.26) km, 16.17 (92.53) km, and 100.95 (174.79) km, respectively. Furthermore, it has been possible to estimate the occurrence altitudes for 81.92% (684 out of 835) of the TIPP events. The altitude deviations, as determined by comparing them with the GHMLLS-SCL method’s locating results, exhibit an arithmetic mean of 2.08 km, a geometric mean of 1.30 km, and a standard deviation of 2.26 km. The outcomes of this research establish a foundation for deeper investigation into the origins of various event types, their seasonal variations, and their geographical distribution patterns. Moreover, they pave the way for utilizing a single satellite to measure global surface reflectance, thus contributing valuable data for meteorological and atmospheric studies.

Root segmentation of horticultural plants in X-Ray CT images by integrating 2D instance segmentation with 3D point cloud clustering

X-ray computed tomography (CT) is a powerful tool for in situ plant root system architecture (RSA) characterization. Accurate root segmentation from CT images is integral to studying RSA. Research studies on segmenting roots from CT images have been mainly limited to image processing-based approaches which may require parameter tuning and often lack common segmentation metrics, e.g., Dice and IoU. A recent deep learning approach utilizes a volumetric encoder-decoder network to achieve a high Dice score and IoU. However, training a volumetric model is dependent on the availability of fully annotated scans of the growing medium column, obtaining which can be time-consuming, tedious, and resource intensive. In this study, an efficient method using deep learning-based instance segmentation in conjunction with density-based spatial clustering of applications with noise (DBSCAN)-based filtering was developed and evaluated for two horticultural plant species. A pretrained Mask R-CNN model was fine-tuned on images selected along different axes of the three-dimensional scans to identify the best view selection strategy for volumetric root segmentation. DBSCAN was used to filter noise from the volumetric segmentation with an automated parameter tuning technique. The proposed method was evaluated on scans of poinsettias and onions and achieved best average scores of 0.831, 0.839, 0.834, and 0.718 for Precision, Recall, Dice, and IoU, respectively. Further experiments showed reducing the training data to 1 % did not significantly impact the segmentation accuracy. Therefore, the proposed method has promising potential to facilitate RSA analysis with its high utility.

Development of HTC-DBSCAN: A Hierarchical Trajectory Clustering Algorithm with Automated Parameter Tuning

Existing route-clustering methods often fail to identify abnormal sections or similarities between routes, mainly when working with large or long datasets. While sub-route clustering can detect regional patterns, it struggles to accurately capture the overall route structure. The present study proposes a new ship route-clustering method that enhances computational efficiency and noise recognition while addressing these limitations. We refined Automatic Identification System data via four data-cleaning processes and applied a statistical distance measurement to assess ship trajectory similarity. Dimensionality reduction was then used to facilitate clustering. The clustering of ship route similarities is non-parametric and can be applied to datasets not separated based on density to find clusters of various densities. Density-Based Spatial Clustering of Applications (DBSCA) applies to many research fields; using the DBSCA with Noise (DBSCAN) algorithm, we propose an improved DBSCAN algorithm that automatically determines the parameters Epsilon and MinPts. In this study, as a core ship route-clustering process, we propose a sub-route clustering process by setting the distance and density of data points to clear standards for re-analysis and completion. The proposed approach demonstrates markedly enhanced clustering performance, offering a more sophisticated and efficient basis for ship route decision-making.

Segmentation of coronary arteries from X-ray angiographic images using density based spatial clustering of applications with noise (DBSCAN)

Coronary heart disease is one of the most fatal illnesses. Its critical role in the prevention and diagnosis of cardiovascular conditions has made the segmentation of cardiovascular images a growing area of research in the medical field. This study introduces a new method for segmenting coronary arteries in X-ray angiographic images using the Density-Based Spatial Clustering of Applications with Noise (DBSCAN) algorithm. This algorithm is capable of restoring the vessel tree pixels incrementally by adjusting two parameters, from a single pixel to values where the thin vessels are detected. In this approach, thick and thin veins are initially separated into two distinct spaces and later merged. The algorithm uses morphological techniques such as reconstruction, skeletonization, pruning, and dilation to remove noise and achieve the final extraction of the vessel tree. The segmented vessel tree reveals several new, thin vessels that exhibit low light intensity in the original image. These vessels align with the ground truth field images, demonstrating the efficacy of the algorithm. The evaluation metrics, including an accuracy of 0.9729, specificity of 0.9768, and sensitivity of 0.9027, indicate highly favorable results. Ultimately, various segmented images illustrate the nature of vessel obstructions.