Distance Metrics Research Articles

Developing WasteSAM: A novel approach for accurate construction waste image segmentation to facilitate efficient recycling

The escalating volume of construction activities and resultant waste generation underscores the imperative for developing sophisticated segmentation models to facilitate efficient sorting and recycling processes. This study introduces WasteSAM, an enhanced iteration of the segment anything model (SAM), specifically tailored to address the intricate complexities inherent in construction waste imagery. Drawing upon a comprehensive dataset comprising over 15,000 masks representing five distinct categories of construction materials, WasteSAM exhibits notably superior segmentation capabilities. Quantitative analysis demonstrates significant performance improvements, with WasteSAM outperforming the original SAM model by an average of 23.9% in dice similarity coefficient and 30.0% in normalized surface distance metrics. The integration of stereo-image techniques in refining the training dataset has facilitated WasteSAM in more accurately discerning the three-dimensional structure of waste materials, thereby augmenting the precision of waste classification. Noteworthy is the model’s adeptness in handling intricate textures and patterns across diverse imaging modalities, including varying lighting conditions and complex object interactions. While showing promising results, this study also highlights the need for high-quality, diverse datasets that reflect real-world construction site complexities, rather than merely larger datasets.

WKNN-Based Wi-Fi Fingerprinting with Deep Distance Metric Learning via Siamese Triplet Network for Indoor Positioning

Weighted k-nearest neighbor (WKNN)-based Wi-Fi fingerprinting is popular in indoor location-based services due to its ease of implementation and low computational cost. KNN-based methods rely on distance metrics to select the nearest neighbors. However, traditional metrics often fail to capture the complexity of indoor environments and have limitations in identifying non-linear relationships. To address these issues, we propose a novel WKNN-based Wi-Fi fingerprinting method that incorporates distance metric learning. In the offline phase, our method utilizes a Siamese network with a triplet loss function to learn a meaningful distance metric from training fingerprints (FPs). This process employs a unique triplet mining strategy to handle the inherent noise in FPs. Subsequently, in the online phase, the learned metric is used to calculate the embedding distance, followed by a signal-space distance filtering step to optimally select neighbors and estimate the user’s location. The filtering step mitigates issues from an overfitted distance metric influenced by hard triplets, which could lead to incorrect neighbor selection. We evaluate the proposed method on three benchmark datasets, UJIIndoorLoc, Tampere, and UTSIndoorLoc, and compare it with four WKNN models. The results show a mean positioning error reduction of 3.55% on UJIIndoorLoc, 16.21% on Tampere, and 16.49% on UTSIndoorLoc, demonstrating enhanced positioning accuracy.

From “open ocean” to “exposed aquaculture”: why and how we are changing the standard terminology describing “offshore aquaculture”

The term “offshore” with regards to aquaculture has hitherto encompassed various perspectives, including technology, geographic location, legal jurisdiction, and more. To resolve the ambiguity in this term and understand its implications for current and future aquaculture development, “offshore” should be resolved into two separate metrics: distance from shore and energy exposure. The United Nations Convention on the Law of the Sea (UNCLOS) distinguishes between internal waters, territorial sea, contiguous zone, exclusive economic zone (EEZ), and the high seas, but currently has no precise definition for “offshore” in its provisions, and therefore no applicable laws pertaining to “offshore” aquaculture. Regulating a multi-technology aquaculture sector may require integrating new spatial concepts into the law rather than merely adapting and extending current regulatory designs to include new production concepts. The metrics of distance from shore and exposure are seen as a range rather than a specific threshold, allowing for a continuum. Distance from shore is readily quantified as a distance from a baseline. To rigorously quantify the exposure, the influence and interactions of oceanic parameters (water depth, water current, and wave height and period) we utilized to generate six indices. These oceanic parameters are seen as the main contributions which influence the physical and some biological parameters required for site, species, and technology selection. Four shellfish, three seaweed, and three finfish sites along with 20 potential aquaculture sites were examined using the indices in association with the energy index to determine tolerances of the structures and their ability to cultivate their relevant species. Two indices, Specific Exposure Energy (SEE) and Exposure Velocity (EV), were selected for utilization in the analysis of sites based on their ease of use and applicability. The interaction between the energy indices and various aspects of farm operations and performance were explored. The indices developed and used in the case studies presented have been shown to be useful tools in the general assessment of the energy that will influence the species and equipment selection at potential aquaculture sites. The indices do not provide a definitive answer as to the potential financial success of a site as this requires other inputs relating to infrastructure costs, annual production, distance from port, sales strategy, etc. However, the Specific Exposure Energy index creates a useful tool to describe site energy and be comprehensible to a wide range of stakeholders. We recommend the SEE index be adopted as the predominant tool to communicate the exposure level of aquaculture sites.

Novel metrics for tracking blood pressure changes incontinuous cuffless blood pressure estimations

Recent studies revealed the importance of tracking continuous blood pressure (BP) changes in monitoring and controlling hypertension and diagnosing cardiovascular diseases. However, current evaluation protocols utilize distance measures as primary metrics, which cannot properly evaluate the ability of the estimation model to track BP changes. This paper proposes a comprehensive evaluation framework which evaluates the distance and trend similarity metrics, and the composite metric of both between the reference and estimated BPs. The results of applying both widely used conventional metrics and the new proposed metrics for BP estimations are demonstrated in an example of comparing the reference with a set of different BP estimations. Then, the metrics are applied to BP estimations obtained using state-of-the-art (SOTA) algorithms. It is shown that even though SOTA algorithms have a low mean and standard deviation of absolute difference, they are not capable of tracking short-term blood pressure changes. Additionally, the proposed metrics are normalized metrics and range from -1 to 1, making them intuitively interpretable, similar to well-known correlation coefficients. Therefore, we suggest that the proposed evaluation framework should be used regularly in evaluating continuous BP monitoring systems.

Hidden diversity in anthropophilic sand flies of the Monticola Series (Diptera, Psychodidae)

The Monticola series comprises two anthropophilic and widely distributed species in Brazil: Pintomyia (Pifanomyia) monticola (Costa Lima, 1932) and Pintomyia (Pifanomyia) misionensis (Castro, 1959). They mainly occur in the Atlantic Rainforest, and it is known that Pi. monticola comprises at least two well-structured genetic lineages regarding a fragment of the cytochrome c oxidase subunit I (COI) gene. Here, we aim to elucidate the taxonomic status of this group using integrative taxonomy tools. Collections were performed in nine localities of four Brazilian states, and COI fragments were sequenced and merged with publicly available data. Several single-locus species delimitation algorithms, genetic distance metrics, phylogenetic trees, and haplotype networks were used to uncover cryptic diversity and population structure within Pi. monticola and Pi. misionensis. The resulting genetic clusters were then tested for morphological differences through linear and geometric morphometry of several characters. We analyzed 152 COI sequences, comprising 48 haplotypes. The maximum intraspecific p distances were 8.21% (mean 4.17%) and 9.12% (mean 4.4%) for Pi. monticola and Pi. misionensis, respectively, while interspecific ones ranged from 10.94 to 14.09% (mean 12.33%). Phylogenetic gene trees showed well-supported clades for both species, with clear structuring patterns within them. Species-delimitation algorithms split our dataset into at least three putative species for each taxon. Moreover, population structure analysis showed a strong correlation between Atlantic Forest areas of endemism as sources of molecular variation in Pi. monticola. Morphometric analyses were significant for wing shape variation and some linear measurements (mainly of the head) when comparing specimens of different genetic clusters for both taxa. These results indicate strong genetic structuring of Monticola series species, confirmed by morphometry, indicating two possible cryptic species complexes.

Optimal allocation model of port emergency resources based on the improved multi-objective particle swarm algorithm and TOPSIS method

The busy maritime traffic and occurrence of ship accidents have led to a growing recognition of the necessity to maritime emergency resources allocation. The port emergency resource allocation is of significant importance for the maritime safety. This paper presents an optimized allocation model for port emergency resources based on the improved multi-objective particle swarm optimization (IMOPSO). The model introduces the crowding distance and improves the external archive update strategy. The particle inertia weight is adjusted and a dynamic mutation operator is incorporated. The entropy-weighted technique for order preference by similarity to an ideal solution method is also employed to identify the optimal solution. A comprehensive comparison with MOPSO has been presented and discussed. Three metrics of generational distance (GD), spacing (SP) and delta indicator (Δ) were employed for performance evaluation. The results demonstrated that the proposed IMOPSO algorithm exhibited superior performance and robustness, with average values of GD = 0.0386, SP = 0.0023 and Δ = 0.6468 for ZDT test functions. The model efficacy is further validated by a case study of oil spill dispersant configuration at Zhanjiang Port, China. Seven alternative schemes have been obtained, among which the optimal scheme is selected by the entropy-weighted TOPSIS method. The overall cost is potentially to be reduced by approximately 33.03 %. The present study would provide a reference for the water pollutant control and environmental management in port waters.

WIFI Fingerprint Correction for Indoor Localization Based on Distance Metric Learning

WIFI Fingerprint Correction for Indoor Localization Based on Distance Metric Learning

Goal-driven long-term marine vessel trajectory prediction with a memory-enhanced network

Enhancing the precision of marine vessel trajectory prediction (VTP) is crucial for collision avoidance, intelligent navigation, and crisis alert in maritime safety. Most RNN-based methods typically face memory weakening issues during long-sequence propagation, leading to the discarding of some key features and significant predictive error accumulation over extended time intervals. Moreover, they struggle to forecast those complex trajectories involving abnormal maneuvers such as sudden acceleration or deceleration, sharp turns, or U-turns, resulting in poor generalization capabilities. To address these pivotal challenges, this paper proposes a novel Memory-Enhanced Network (MENet) for VTP, catering to intricate sailing intention modeling with long-term motion pattern perception. Specifically, we design an embeddable memory-enhanced block (MEB) that adaptively aggregates memory vectors across multiple temporal scales to assist in better prediction without disrupting the original backbone structure. Also, a goal-driven vessel trajectory decoder (GD-VTD) is developed to facilitate reliable model inferences by combining vessel type and destination variables as guidance information. Furthermore, we reconstruct the traditional loss function based on relative distance metrics, incorporating predicted headings into the optimization process to generate consistent trajectories that comply with realistic vessel dynamics. Ultimately, MENet could learn diverse sailing intentions by assembling the above parts to predict long-term marine vessel trajectories. Extensive experimental results on Automatic Identification System (AIS) datasets from three coastal regions in the US demonstrate that our model exhibits superior accuracy and robustness compared to other baselines. Specifically, on the Everglades Port (EP) dataset, our method reduces MAE, RMSE, and MAPE errors by 7.25%, 7.82%, and 7.62%, respectively, compared to the existing best results during this experiment. This is another piece of evidence for the effectiveness of goal-driven trajectory prediction in real-world maritime settings.

Spectral cluster supertree: fast and statistically robust merging of rooted phylogenetic trees.

The algorithms for phylogenetic reconstruction are central to computational molecular evolution. The relentless pace of data acquisition has exposed their poor scalability and the conclusion that the conventional application of these methods is impractical and not justifiable from an energy usage perspective. Furthermore, the drive to improve the statistical performance of phylogenetic methods produces increasingly parameter-rich models of sequence evolution, which worsens the computational performance. Established theoretical and algorithmic results identify supertree methods as critical to divide-and-conquer strategies for improving scalability of phylogenetic reconstruction. Of particular importance is the ability to explicitly accommodate rooted topologies. These can arise from the more biologically plausible non-stationary models of sequence evolution. We make a contribution to addressing this challenge with Spectral Cluster Supertree, a novel supertree method for merging a set of overlapping rooted phylogenetic trees. It offers significant improvements over Min-Cut supertree and previous state-of-the-art methods in terms of both time complexity and overall topological accuracy, particularly for problems of large size. We perform comparisons against Min-Cut supertree and Bad Clade Deletion. Leveraging two tree topology distance metrics, we demonstrate that while Bad Clade Deletion generates more correct clades in its resulting supertree, Spectral Cluster Supertree's generated tree is generally more topologically close to the true model tree. Over large datasets containing 10,000 taxa and 500 source trees, where Bad Clade Deletion usually takes 2 h to run, our method generates a supertree in on average 20 s. Spectral Cluster Supertree is released under an open source license and is available on the python package index as sc-supertree.

Development and evaluation of a novel framework to enhance k-NN algorithm’s accuracy in data sparsity contexts

This paper presents a novel framework for implementing the k-NN algorithm, designed to enhance its accuracy in contexts with sparse data. The framework addresses limitations in the algorithm’s training process by optimizing data structures. It employs composite datasets generated from the initial data using a data-driven fuzzy Analytic Hierarchy Process weighting scheme. This approach is designed to enhance the informational content in the initial datasets, thus reducing the entropy and implementation uncertainty. The framework was evaluated using 75 publicly available datasets and 3 generated datasets, demonstrating significant accuracy improvements across various k-parameter values. The findings were rigorously generalized using non-parametric hypothesis tests; while the resulting sensitivity was assessed by applying different distance metrics. By enhancing informational content, the composite data structures contribute to both accuracy improvements and scalability, particularly in data-sparse contexts. This relationship underscores the critical role of entropy in enhancing the performance of explainable machine learning algorithms, providing a valuable and interpretable tool for transforming data structures in sparse data environments.

Encoder embedding for general graph and node classification

Graph encoder embedding, a recent technique for graph data, offers speed and scalability in producing vertex-level representations from binary graphs. In this paper, we extend the applicability of this method to a general graph model, which includes weighted graphs, distance matrices, and kernel matrices. We prove that the encoder embedding satisfies the law of large numbers and the central limit theorem on a per-observation basis. Under certain condition, it achieves asymptotic normality on a per-class basis, enabling optimal classification through discriminant analysis. These theoretical findings are validated through a series of experiments involving weighted graphs, as well as text and image data transformed into general graph representations using appropriate distance metrics.

A smartphone-based human activities recognition using novel multi-stream movelets on fusion of accelerometer and gyroscope data and classification using different distance metrics

A smartphone-based human activities recognition using novel multi-stream movelets on fusion of accelerometer and gyroscope data and classification using different distance metrics

Sorlinia euscelidii gen. nov., sp. nov., a novel acetic acid bacterium isolated from the leafhopper Euscelidius variegatus (Hemiptera: Cicadellidae).

Acetic acid bacteria - belonging to the Acetobacteraceae family - are found in the gut of many sugar-feeding insects. In this study, six strains have been isolated from the hemipteran leafhopper Euscelidius variegatus. While they exhibit high 16S rRNA gene sequence similarities to uncultured members of the Acetobacteraceae family, they could not be unequivocally assigned to any particular type species. Considering the clonality of the six isolates, the EV16PT strain was used as a representative of this group of isolates. The genome sequence of EV16PT is composed of a 2.388 Mbp chromosome, with a DNA G+C content of 57 mol%. Phylogenetic analyses based on the 16S rRNA gene sequence and whole-genome multilocus sequence analysis indicate that EV16PT forms a monophyletic clade with the uncultivated endosymbiont of Diaphorina citri, the Candidatus Kirkpatrickella diaphorinae. Such a phylogenetic clade is positioned between those of Asaia-Swaminathania and Kozakia. The genomic distance metrics based on gene and protein sequences support the proposal that EV16PT is a new species belonging to a yet-undescribed genus. It is a rod-shaped Gram-stain-negative bacterium, strictly aerobic, non-motile, non-spore-forming, showing optimal growth without salt (NaCl) at 30 °C and pH of 6-7. The major quinone is Q10, and the dominant cellular fatty acids (>10%) are C18:l ω7c, C19 : 0 cyclo ω6c, C16 : 0 and C19 : 1 2OH. The polar lipid profile comprises diphosphatidylglycerol, phosphatidylethanolamine and phosphatidylcholine, along with unidentified aminophospholipids, glycophospholipids, aminolipids and lipids. Based on a polyphasic approach, including phylogenetic, phylogenomic, genome relatedness, phenotypic and chemotaxonomic characterisations, EV16PT (= KCTC 8296T, = DSM 117028T) is proposed as a representative of a novel species in a novel genus with the proposed name Sorlinia euscelidii gen. nov., sp. nov., in honour of Prof. Claudia Sorlini, an Italian environmental microbiologist at the University of Milan who inspired the research on microbial diversity, including symbiosis in plants and animals.

Research on a Multi-Scale Clustering Method for Buildings Taking into Account Visual Cognition

Building clustering is a key problem that needs to be solved in the realization of the automatic synthesis of large-scale maps. The selection of different feature and spatial distance calculation methods has a great impact on the clustering results, and the need to manually select appropriate feature and distance metrics leads to the problem of not being able to fully consider the complexity and diversity of buildings. In this paper, we propose a multi-scale clustering method for buildings that takes visual perception into account using the Gestalt principle to simulate how humans classify buildings through visual perception. Moreover, by analyzing the spatial features and texture attributes of buildings, a visual distance is designed to be used as a condition for building classification to assess the similarity between buildings, solving the complexity of manually selecting feature vectors and spatial distances and realizing the adaptive selection of features. Through experimental validation at different scales (macro, meso and micro), the present method is able to achieve the accurate clustering of buildings, and a frequency threshold of 91% is found, which is able to determine the optimal clustering results. The experimental results show that the proposed method can not only fully consider the complexity and diversity of buildings but also effectively support the understanding and analysis of urban spatial structure and provide a scientific decision-making basis for urban planning and management.

Drone-Based Intelligent System for Social Distancing Compliance Using YOLOv5 and YOLOv6 with Euclidean Distance Metric

Drone-Based Intelligent System for Social Distancing Compliance Using YOLOv5 and YOLOv6 with Euclidean Distance Metric

Computational identification of surface markers for isolating distinct subpopulations from heterogeneous cancer cell populations

Intratumor heterogeneity reduces treatment efficacy and complicates our understanding of tumor progression and there is a pressing need to understand the functions of heterogeneous tumor cell subpopulations within a tumor, yet systems to study these processes in vitro are limited. Single-cell RNA sequencing (scRNA-seq) has revealed that some cancer cell lines include distinct subpopulations. Here, we present clusterCleaver, a computational package that uses metrics of statistical distance to identify candidate surface markers maximally unique to transcriptomic subpopulations in scRNA-seq which may be used for FACS isolation. With clusterCleaver, ESAM and BST2/tetherin were experimentally validated as surface markers which identify and separate major transcriptomic subpopulations within MDA-MB-231 and MDA-MB-436 cells, respectively. clusterCleaver is a computationally efficient and experimentally validated workflow for identification of surface markers for tracking and isolating transcriptomically distinct subpopulations within cell lines. This tool paves the way for studies on coexisting cancer cell subpopulations in well-defined in vitro systems.

Semi-supervised segmentation of cardiac chambers from LGE-CMR using feature consistency awareness

BackgroundLate gadolinium enhancement cardiac magnetic resonance imaging (LGE-CMR) is a valuable cardiovascular imaging technique. Segmentation of cardiac chambers from LGE-CMR is a fundamental step in electrophysiological modeling and cardiovascular disease diagnosis. Deep learning methods have demonstrated extremely promising performance. However, excellent performance often depended on a large amount of finely annotated data. The purpose of this manuscript was to develop a semi-supervised segmentation method to use unlabeled data to improve model performance.MethodsThis manuscript proposed a semi-supervised network that integrates triple-consistency constraints (data-level, task-level, and feature-level) for cardiac chambers segmentation from LGE-CMR. Specifically, we designed a network that integrated segmentation and edge prediction tasks based on the mean teacher architecture. This addressed the problem of ignoring some challenging regions because of excluding low-confidence regions of previous research. We also applied a voxel-level contrastive learning strategy to achieve feature-level consistency, helping the model pay attention to the consistency between features overlooked in previous research.ResultsIn terms of the Dice, Jaccard, Average Surface Distance (ASD), and 95% Hausdorff Distance (95HD) metrics, for the atrial segmentation dataset, the proposed method achieved scores of 88.34%, 79.30%, 7.92, and 2.02 when trained with 10% labeled data, and 90.70%, 83.09%, 6.41, and 1.72 when trained with 20% labeled data. For the ventricular segmentation task, the results were 87.22%, 77.95%, 2.27, and 0.61 with 10% labeled data, and 88.99%, 80.45%, 1.87, and 0.51 with 20% labeled data, respectively.ConclusionExperiments demonstrated that our method outperforms previous semi-supervised methods, showing the potential of the proposed network for semi-supervised segmentation problems.

Optimal Illumination Distance Metrics for Person Re-identification in Complex Lighting Conditions

Person Re-identification is extensively applied in public security and surveillance. However, environmental factors like time and location often lead to varying lighting conditions in captured pedestrian images, significantly impacting identification accuracy. Current approaches mitigate this issue through lighting transformation techniques, aiming to normalize images to a standard lighting condition for consistent person re-identification results. Yet, these methods overlook the fact that different content may hold distinct identification values under diverse lighting conditions. To address this, we conducted an analysis on the identification distance between images of the same or different pedestrians under predefined lighting conditions. From this analysis, we introduce the concept of optimal lighting: a condition where the distance between image pairs is minimized compared to other lighting scenarios. We propose utilizing this optimal lighting distance in the image retrieval process for final ranking. Our study, validated on synthetic datasets Market-IA and Duke-IA, demonstrates that optimal lighting is independent of image texture information. Each image pair exhibits a unique optimal lighting, yet consistently shows a minimum distance value.

New Fermatean Fuzzy Distance Metric and Its Utilization in the Assessment of Security Crises Using the MCDM Technique

The problem of insecurity is a global phenomenon that has several forms like terrorism, banditry, kidnappings, etc. Insecurity has taken hold in the Sub-Saharan Region of West Africa, especially in Nigeria, for over two decades. Nigeria’s security crisis is more pronounced in the Northern Region, with a new wave in the North-Central Region of Nigeria. It is herculean to assess insecurity in the North-Central Region of Nigeria because of the region’s fuzzy or imprecise nature of insecurity. This constitutes the rationale for deploying the Fermatean fuzzy technique to assess insecurity due to the capacity of the Fermatean fuzzy scheme to handle imprecision. To this end, a new Fermatean fuzzy distance metric is presented to evaluate insecurity in the North-Central Region of Nigeria using a multi-criteria decision-making technique. To express the logic for creating the new Fermatean fuzzy distance metric, some existing Fermatean fuzzy distance metrics are discussed, along with their drawbacks. The mathematical properties of the new technique are discussed, and the new method is applied computationally to assess insecurity in the North-Central Region of Nigeria. The data for the security assessment are collected via Fermatean fuzzy linguistic variables using the opinions of security experts and analyzed using the technique for order of preference by similarity to ideal solution, which is a commonly used multi-criteria decision-making method. Finally, the numerical validity of the new technique is expressed with comparative results, and the finding shows the benefit of the new distance approach over the existing methodologies. The outcome of the work will provide reliable traveling advisories for safe voyages within the region.

Recovering MRI magnetic field strength properties using machine learning based on image compression quality scores

AbstractOver the years, significant hardware advancements have led to higher magnetic field MRI (Magnetic Resonance Imaging) acquisitions, providing improved diagnostic image quality at a higher cost. While higher image quality is desired, the investment required for high-field MRI imaging systems remains a significant consideration. Furthermore, historical patient records may still contain low-field magnetic strength MRI data. In this work, we present how image compression quality scores of MRI images could be used to recover their magnetic field strength properties. This work presents an interesting inverse problem scenario where output properties are used to recover an input property of an image. We implemented supervised machine learning models that utilize compressed image quality scores - based on Mean Squared Error (MSE), Structural Similarity Index (SSIM), Visual Information Fidelity (VIF), and Earth Movers Distance (EM) metrics - as inputs. These models classify images into specific classes of magnetic field strength at which they were acquired (Low, Medium, and High) based solely on the quality scores of their compressed copies. The trained machine learning models (Support Vector Machine (SVM), Logistic Regression, K-nearest Neighbours (KNN), Decision Tree and Random Forest) achieved nearly 100% performance efficiency based on accuracy and F-1 score for all considered quality measures. This comprehensive evaluation offers insights into how compression techniques and quality factors impact image fidelity across various MRI magnetic field strengths. The findings of this study may prove valuable in recovering missing meta-tag information in historical image DICOM records and Context-Based Retrieval Systems (CBRS). The approach of using quality scores as features in training machine learning models, as demonstrated in this work, can be extended to other image groups where input parameters create statistically significant distinctions or are challenging to extract from images.