Distance Metrics Research Articles

Three-dimensional convolutional neural network for leak detection and localization in smart water distribution systems

Smart meters such as advanced metering infrastructure (AMI) can significantly improve identifying realistic sized leaks in water distribution networks (WDNs). However, to date, detection/localization methods for AMI systems are extremely limited. In this study, to examine the benefits of using AMIs for leak detection within distribution network, a three-dimensional (3D) convolutional neural network (CNN) deep learning (DL) model is proposed that can account for temporally and spatially distributed information of pressures. The 3D CNN is tested for a real WDN in Austin using the realistic sized leaks (e.g., 3 L/s for 150-mm pipes) that are generated from hydraulic simulations. The model's performance is evaluated using detection probability, false alarm rate, and localization pipe distance metrics. In addition, the strength of using DL for leak identification is examined by comparing the CNN results with those from an optimization-based model. The 3D CNN performed better than the optimization model indicating that DL has advantages over conventional tools such as optimization methods. However, its adaptability may limit its use in some cases. Since DL can be significantly impacted by hydraulic simulation model, a way to handle modelling error must be determined. In addition, as network changes occur, retraining is required that may be time consuming and have difficulty with the number of failure conditions.

Mixed fuzzy C-means clustering

Clustering analysis becomes challenging when the dataset has mixed data types comprising categorical (nominal or ordinal scale) and numerical (interval scale) features. Mainstream distance metrics cannot handle the information in categorical data about the similarity between the observations and cluster centers, leading to performance loss. Various methods are introduced in the literature to handle the mixed data types in clustering. However, each method has disadvantages in capturing categorical information about similarity, adjusting the contribution of categorical information to clustering, and computational or implementation inefficiency. This study proposes a mixed fuzzy C-means clustering method for mixed data types. Two new distance metrics are developed to handle binary and multi-class nominal features. The scaled entropy of each data type is used to adjust the weight of each data type in the overall similarity metric, providing a lower bias since no user-specified weight is required. A comparative numerical study is conducted with twenty real datasets and seven benchmark methods using five cluster validation statistics. The mixed fuzzy C-means clustering performs better than the benchmark methods and is computationally efficient in practice. Since all the computer codes for implementing mixed fuzzy C-means clustering are given, the proposed method is readily applicable to practical problems.

Fault Diagnosis of Induction Motors under Limited Data for Across Loading by Residual VGG-Based Siamese Network

This study proposes an improved few-shot learning model of the Siamese network residual Visual Geometry Group (VGG). This model combined with time–frequency domain transformation techniques effectively enhances the performance of across-load fault diagnosis for induction motors with limited data conditions. The proposed residual VGG-based Siamese network consists of two primary components: the feature extraction network, which is the residual VGG, and the merged similarity layer. First, the residual VGG architecture utilizes residual learning to boost learning efficiency and mitigate the degradation problem typically associated with deep neural networks. The employment of smaller convolutional kernels substantially reduces the number of model parameters, expedites model convergence, and curtails overfitting. Second, the merged similarity layer incorporates multiple distance metrics for similarity measurement to enhance classification performance. For cross-domain fault diagnosis in induction motors, we developed experimental models representing four common types of faults. We measured the vibration signals from both healthy and faulty models under varying loads. We then applied the proposed model to evaluate and compare its effectiveness in cross-domain fault diagnosis against conventional AI models. Experimental results indicate that when the imbalance ratio reached 20:1, the average accuracy of the proposed residual VGG-based Siamese network for fault diagnosis across different loads was 98%, closely matching the accuracy of balanced and sufficient datasets, and significantly surpassing the diagnostic performance of other models.

Development of a Children’s Educational Dictionary for a Low-Resource Language Using AI Tools

Today, various interactive tools or partially available artificial intelligence applications are actively used in educational processes to solve multiple problems for resource-rich languages, such as English, Spanish, French, etc. Unfortunately, the situation is different and more complex for low-resource languages, like Kazakh, Uzbek, Mongolian, and others, due to the lack of qualitative and accessible resources, morphological complexity, and the semantics of agglutinative languages. This article presents research on early childhood learning resources for the low-resource Kazakh language. Generally, a dictionary for children differs from classical educational dictionaries. The difference between dictionaries for children and adults lies in their purpose and methods of presenting information. A themed dictionary will make learning and remembering new words easier for children because they will be presented in a specific context. This article discusses developing an approach to creating a thematic children’s dictionary of the low-resource Kazakh language using artificial intelligence. The proposed approach is based on several important stages: the initial formation of a list of English words with the use of ChatGPT; identification of their semantic weights; generation of phrases and sentences with the use of the list of semantically related words; translation of obtained phrases and sentences from English to Kazakh, dividing them into bigrams and trigrams; and processing with Kazakh language POS pattern tag templates to adapt them for children. When the dictionary was formed, the semantic proximity of words and phrases to the given theme and age restrictions for children were taken into account. The formed dictionary phrases were evaluated using the cosine similarity, Euclidean similarity, and Manhattan distance metrics. Moreover, the dictionary was extended with video and audio data by implementing models like DALL-E 3, Midjourney, and Stable Diffusion to illustrate the dictionary data and TTS (Text to Speech) technology for the Kazakh language for voice synthesis. The developed thematic dictionary approach was tested, and a SUS (System Usability Scale) assessment of the application was conducted. The experimental results demonstrate the proposed approach’s high efficiency and its potential for wide use in educational purposes.

Assessing phylogenetic diversity metrics in terrestrial ecological restoration: global trends and gaps

Phylogenetic diversity (PD) metrics estimate community diversity through evolutionary relationships, yet their potential in restoration ecology remains underutilized. This study reviews the literature on ecological restoration of terrestrial vegetation to evaluate the use of PD metrics, focusing on their application, global trends, and existing research gaps. Most studies were conducted in the United States, China, and Brazil, primarily in temperate broadleaf mixed forests (36.36%) and tropical and subtropical moist broadleaf forests (33.33%). Half of the papers were based on observational studies of restorations, and the other half were experimental studies. Plant PD was the primary focus in 90.09% of papers, with grasses and trees being the most studied life forms. Standardized effect size of the mean pairwise distance and mean nearest taxonomic distance metrics were the most commonly used metrics. The majority of studies used PD as a response variable and restoration indicators (e.g. age, initial seed/seedling mixture, and restoration impact) as explanatory variables. Research bias toward grassland and limited studies in Africa and Oceania were noted. Future studies should broaden geographic coverage in restoration to provide a more comprehensive understanding of PD dynamics globally. Also, efforts should be made to expand the taxonomic scope beyond to capture the full spectrum of biodiversity in restoration assessments.

ADCMDES: Design of an augmented cross-domain collaborative recommendation model using novel distance metric and ensemble stratification

Collaborative recommendation involves leveraging information from one entity to suggest attributes of other entities through pattern analysis. These models are invaluable for understanding data behaviour’s impact on related entities. Researchers propose various pattern recognition and correlation models, employing distance metrics like Jaccard, Cosine, etc., to estimate correlations between user queries and recommendation datasets. However, these models become less efficient as dataset size increases due to exponential correlation estimation delays. To enhance scalability while retaining recommendation quality, a new approach is introduced: ADCMDES. This novel augmented cross-domain collaborative model employs a hybrid distance metric and ensemble stratification for dataset pruning. It operates semi-supervisedly, requiring information about the entities being collaborated upon. This data is used to cluster similar collaborative entities, producing a condensed cluster with greater relevancy to user queries. Utilizing word2vec, records are transformed into features for an ensemble classification engine. The resultant model categorizes user input, directing it to the most relevant cluster. Entries within this cluster are ranked using a hybrid metric amalgamating 18 distance measures, enhancing correlation between input queries and recommendations. In testing, ADCMDES exhibited 15% better accuracy, 8% better precision, 9% better recall, and 3% lower RMSE compared to standard models across datasets. While some delay is introduced due to ensemble classification and augmented feature pooling, this doesn't considerably affect long-term recommendation performance and can be mitigated through parallel processing and redundancy reduction techniques.

Phylogenetic structure and turnover between lowland and montane subtropical forests indicate differential community assembly processes, affected by successional stage and spatial gradients

Secondary forests represent an increasing proportion of global forest cover and offer a range of ecosystem services that are integral to environmental policy targets. Highly disturbed landscapes with temporal records of forest plant community composition offer key insights into the processes that shape plant communities as forests undergo secondary succession. We investigated patterns of plant community phylogenetic structure and phylogenetic beta diversity. Mean pairwise distance (MPD) and Mean Nearest Taxon Distance (MNTD) metrics were determined between co-occurring species within plant communities, in addition to phylogenetic beta diversity metrics relative to null models of random phylogenetic assembly. MPD and MNTD were compared between elevational and successional classes and modelled as products of intercommunity distance (metres) and forest community age (years). Phylogenetic nonmetric multidimensional scaling explored phylogenetic community structure between lowland and montane forest type in Hong Kong. We found that plant communities in secondary forests in Hong Kong exhibited patterns of increased basal phylogenetic clustering with increasing community elevation, while phylogenetic turnover was influenced by spatial and successional factors in lowland and montane forest. Our findings indicate differential community assembly in lowland compared to montane forest type in Hong Kong, as well as evidence for barriers to plant dispersal in secondary forest communities due to patterns of spatial phylogenetic clustering. Plant communities in montane forests were found to be phylogenetically distinct from lowland forest plant communities. Patterns of spatial phylogenetic clustering may suggest significant dispersal or post-dispersal processes causing the clustering of related species at fine spatial scales, while phylogenetic turnover with increasing successional age may indicate compositional changes during the process of passive forest regeneration. Collectively, these results emphasize the need to investigate active pathways for rewilding dispersal limited late successional forest tree species in Hong Kong.

Unsupervised motor incipient fault detection using lightweight network and orthogonal low-rank embedding

Abstract Electrical motor is a key component in industrial systems. Detecting incipient fault of motor is critical to system reliability. However, the characteristics of faults and normal stages are difficult to distinguish, Meanwhile, the lightweight requirements of the model and the imbalance of the samples also make incipient fault detection challenged. To address these problems, this paper proposes an unsupervised fault detection method combines lightweight network and orthogonal low-rank embedding (OLE). The raw signals are firstly transformed into time-frequency images and fed into lightweight convolution network for feature extraction. Then, the features are clustered into orthogonal subspaces to enhance inter-class separability. Finally, a detection module based on distance metric is designed to identify the incipient fault of motor. The effectiveness of the proposed method is validated on four industrial motor dataset and compared with other methods.

Changes in the structure of spontaneous speech predict the disruption of hierarchical brain organization in first-episode psychosis.

Psychosis implicates changes across a broad range of cognitive functions. These functions are cortically organized in the form of a hierarchy ranging from primary sensorimotor (unimodal) to higher-order association cortices, which involve functions such as language (transmodal). Language has long been documented as undergoing structural changes in psychosis. We hypothesized that these changes as revealed in spontaneous speech patterns may act as readouts of alterations in the configuration of this unimodal-to-transmodal axis of cortical organization in psychosis. Results from 29 patients with first-episodic psychosis (FEP) and 29 controls scanned with 7 T resting-state fMRI confirmed a compression of the cortical hierarchy in FEP, which affected metrics of the hierarchical distance between the sensorimotor and default mode networks, and of the hierarchical organization within the semantic network. These organizational changes were predicted by graphs representing semantic and syntactic associations between meaningful units in speech produced during picture descriptions. These findings unite psychosis, language, and the cortical hierarchy in a single conceptual scheme, which helps to situate language within the neurocognition of psychosis and opens the clinical prospect for mental dysfunction to become computationally measurable in spontaneous speech.

Mesh representation matters: investigating the influence of different mesh features on perceptual and spatial fidelity of deep 3D morphable models

BackgroundDeep 3D morphable models (deep 3DMMs) play an essential role in computer vision. They are used in facial synthesis, compression, reconstruction and animation, avatar creation, virtual try-on, facial recognition systems and medical imaging. These applications require high spatial and perceptual quality of synthesised meshes. Despite their significance, these models have not been compared with different mesh representations and evaluated jointly with point-wise distance and perceptual metrics. MethodsWe compare the influence of different mesh representation features to various deep 3DMMs on spatial and perceptual fidelity of the reconstructed meshes. This paper proves the hypothesis that building deep 3DMMs from meshes represented with global representations leads to lower spatial reconstruction error measured with L1 and L2 norm metrics and underperforms on perceptual metrics. In contrast, using differential mesh representations which describe differential surface properties yields lower perceptual FMPD and DAME and higher spatial fidelity error. The influence of mesh feature normalisation and standardisation is also compared and analysed from perceptual and spatial fidelity perspectives. ResultsThe results presented in this paper provide guidance in selecting mesh representations to build deep 3DMMs accordingly to spatial and perceptual quality objectives and propose combinations of mesh representations and deep 3DMMs which improve either perceptual or spatial fidelity of existing methods.

REVOLUTIONIZING MOBILITY: A COMPREHENSIVE EVALUATION OF THE IMPACT OF AI ON AUTOMATED VEHICLES

Automated vehicles (AVs) represent a game-changing advancement in transportation, utilizing cutting-edge technologies to travel without human intervention. These vehicles, which range from advanced driver assistance systems (ADAS) to completely autonomous versions, rely on artificial intelligence (AI) to perceive and make decisions. Recent advances in sensor technology and machine learning have improved AV capabilities, but understanding how AI responds to various distance metrics is critical for assuring safe journeys. Hypothesizing that the more the distance the car is traveling, the more AI may be able to provide a safe journey for the passengers,this study seeks to investigate the complex relationship between distance and AIs ability to ensure AV safety. Investigating the physical, geographical, and temporal characteristics of distance can help optimize AV performance and reduce safety issues.

Forensic analysis of microtraces using image recognition through machine learning

Traces found at a crime scene can be interpreted as vectors of information that help describe the possible dynamics of the crime. However, some analyses show that pattern recognition, especially in materials, is subjective, as it depends on the analyst’s references. Based on this problem, the work aimed to use different statistical methods to establish pattern recognition in silver tapes. For this, two approaches were used, one based on deep learning (convolutional neural networks) and the other using a different method (Pearson’s correlation, distance metrics, and Principal Component Analysis). The dataset comprised four brands of silver-tape available in the retail market in the crime scene region, and fragments of tape originating after the detonation of a handmade explosive device. These materials were analyzed using a Leica DVM6 microscope. In both approaches, it was possible to recognize patterns. In deep learning, it was possible to establish that the fragments came from a common origin. The best model demonstrated that 92.1 % of the real materials questioned were the same silver-tape, with a confidence level of 0.94. By combining the methods, it was possible to observe a trend among the results. These responses demonstrated that using images in a computer vision context could remove the subjectivity of forensic analysis and correlate the microtraces found at a crime scene. In this way, these techniques can open new perspectives for the forensic area, making the interpretation more objective and transparent in its responses to society.

The importance of availability of, proximity to, and use of food retailers in relation to snack consumption – a cross-sectional mediation analysis in the Eet & Leef study

ABSTRACT Food access can have a substantial impact on food consumption and health. International literature suggests that density metrics are best used to measure access to food retailer, with the exception of supermarkets for which distance metrics can also be used. However, whether to use distance or density-based metrics in the Netherlands, which is a densely populated country with short distances to food retailers, is unknown. Using a cross-sectional sample of Dutch adults aged 18–65 years living in cities (N = 1589), we examined correlations between distance to the nearest and distance to the actually visited food retailer. In addition, we examined whether the perceived availability and use of food retailers explains any association between distance from home to the nearest food retailer and snack food consumption. We examined fast food restaurants, regular supermarkets and discount supermarkets. We found that the correlations between the nearest and actual visited food retailer were moderate, ranging from r = .73 (discount supermarkets) to r = .43 (fast food restaurants). For none of the food retailers we found a direct association with snack food consumption, and neither was there evidence for mediation through perceived availability and use of food retailers. In Dutch cities, distance-based metrics may not be a good indicator of food retailer access.

A new approach to K-nearest neighbors distance metrics on sovereign country credit rating

This study introduces feature importance K-nearest neighbors (FIKNN), an innovative adaptation of the K-nearest neighbors (KNN) algorithm tailored for classifying sovereign country credit ratings. The primary objective is to enhance KNN's predictive accuracy by integrating a feature importance mechanism derived from the random forest algorithm, which prioritizes significant features and reduces the impact of less relevant ones, refining the distance computation within KNN. Utilizing a comprehensive dataset of sovereign credit ratings, the performance of FIKNN was assessed against traditional KNN using various feature sets and bootstrap samples. The FIKNN model consistently outperformed the standard KNN by approximately 1% in classification accuracy, attributed to the weighted distance metric adjusting feature influence based on importance. Key findings indicate that FIKNN effectively manages datasets with varying feature relevance and demonstrates a positive correlation between feature diversity and model performance. Future research will explore other distance metrics and refine the feature importance weighting mechanism to broaden FIKNN's applicability in diverse predictive tasks.

On the convergence of phase space distributions to microcanonical equilibrium: dynamical isometry and generalized coarse-graining

Abstract This work explores the manner in which classical phase space distribution functions converge to the microcanonical distribution. We first prove a theorem about the lack of convergence, then define a generalization of the coarse-graining procedure that leads to convergence. We prove that the time evolution of phase space distributions is an isometry for a broad class of statistical distance metrics, implying that ensembles do not get any closer to (or farther from) equilibrium, according to these metrics. This extends the known result that strong convergence of phase space distributions to the microcanonical distribution does not occur. However, it has long been known that weak convergence can occur, such that coarse-grained distributions---defined by partitioning phase space into a finite number of cells---converge pointwise to the microcanonical distribution. We define a generalization of coarse-graining that removes the need for partitioning phase space into cells. We prove that our generalized coarse-grained distribution converges pointwise to the microcanonical distribution if the dynamics are strong mixing. As an example, we study an ensemble of triangular billiard systems.

The role of encodings and distance metrics for the quantum nearest neighbor

Over the past few years, we observed a rethinking of classical artificial intelligence algorithms from a quantum computing perspective. This trend is driven by the peculiar properties of quantum mechanics, which offer the potential to enhance artificial intelligence capabilities, enabling it to surpass the constraints of classical computing. However, redesigning classical algorithms into their quantum equivalents is not straightforward and poses numerous challenges. In this study, we analyze in-depth two orthogonal designs of the quantum K-nearest neighbor classifier. In particular, we show two solutions based on amplitude encoding and basis encoding of data, respectively. These two types of encoding impact the overall structure of the respective algorithms, which employ different distance metrics and show different performances. By breaking down each quantum algorithm, we clarify and compare implementation aspects ranging from data preparation to classification. Eventually, we discuss the difficulties associated with data preparation, the theoretical advantage of quantum algorithms, and their impact on performance with respect to the classical counterpart.

Fixed-Point and Random Fixed-Point Theorems in Preordered Sets Equipped with a Distance Metric

This paper explores fixed points for both contractive and non-contractive mappings in traditional b-metric spaces, preordered b-metric spaces, and random b-metric spaces. Our findings provide insights into the behavior of mappings under various constraints and extend our approach to include coincidence and common fixed-point theorems in these spaces. We present new examples and graphical representations for the first time, offering novel results and enhancing several related findings in the literature, while broadening the scope of earlier works of Ran and Reurings, Nieto and Rodríguez-López, Górnicki, and others.

417 Impact of virtual fence technology on yearling steer behavior and performance

Abstract Virtual fencing (VF) has the capacity to transform the landscape of livestock management within extensive rangeland systems. The objective of this study was to evaluate the effect of Vence (Merck & Co., Inc., Rahway, NJ) VF technology on yearling steer behavior and performance. Steers were allocated into one of two grazing systems [continuous grazing (CG) or rotational grazing (RG) managed using VF] across three different stocking rates (light, moderate, and heavy, 0.32, 0.40, and 0.72 animal unit months, respectively) for three grazing seasons. Based on initial body weight, steers were randomly blocked into six pastures (346 ± 39, 273 ± 34, and 319 ± 29 kg, respectively) at the South Dakota State University Cottonwood Field Station (n = 127, 135, and 127, in 2021, 2022 and 2023, respectively). Steers assigned to the CG treatment had free access to the entire pasture for the duration of the grazing season. Steers assigned to the RG treatment were rotated among virtual ‘paddocks’ for the duration of the grazing season. The days spent grazing in each paddock for the RG treatment were determined based on bi-weekly clip plots for biomass estimation. The VF collars were used to track steer location at 5-min intervals; only steers assigned to the RG treatment were managed with VF boundaries and exposed to auditory and electrical cues from the collars. Raw data was downloaded from Vence Herd Manager through an automatic programming interface and cleaned by removing messages that failed to transmit correctly or were outside the bounds of study site pastures. Animal behavior metrics of daily distance traveled (DDT), daily grazing time, daily resting time, and daily walking time were calculated for each individual animal and averaged by pasture using Program R. Steer weights were collected using SmartScales (C-Lock Inc, Rapid City, SD). Average daily gain (ADG) was calculated using a linear model to develop a regression equation for each individual animal using weight as the dependent variable and day of trial as the independent variable. The slope of the regression line was used to estimate ADG. Individual DDT, behavior, and performance metrics were analyzed using a mixed model analysis of variance (ANOVA) to compare the impact of grazing treatment and stocking rate (fixed effects) with year as the random effect. Treatment did not influence (P > 0.05) grazing, walking, or resting behavior. Similarly, no differences were detected in DDT between treatment groups or across different stocking rates. Furthermore, there were no differences (P > 0.05) in ADG across treatment groups. Implementation of VF had no impact on animal behavior or performance, justifying its use in grazing settings; however, financial and cattle finishing aspects still need to be evaluated to determine its overall benefits and costs.

A lightweight joint metric detection approach on YOLO for hot spots in photovoltaic modules

The hot spot effect is one of the primary causes of damage to photovoltaic (PV) modules and a significant factor contributing to the decline in their power generation capacity. Thermal imaging inspection of PV modules is an indispensable aspect of PV plant operation and maintenance. This article introduces a lightweight detection algorithm for hot spots in PV modules based on an enhanced version of YOLOv8. The algorithm incorporates a lightweight convolution operator, Volumetric Grid Spatial Cross Stage Partial, as a replacement for the original C2f operator, resulting in effective reduction of the model's parameter size and improved detection speed. Additionally, the Content-Aware ReAssembly of FEatures upsampling operator is utilized instead of the nearest-neighbor algorithm during the upsampling process, thereby minimizing the loss of hot spot feature information. Furthermore, a joint metric approach combining the Complete Intersection over Union metric and the normalized Wasserstein distance metric is proposed to calculate the localization loss of the target bounding boxes, thereby enhancing the regression accuracy of small hot spot prediction boxes. Experimental results demonstrate that the improved YOLOv8 network enables fast and accurate detection of hot spots. This method achieves an impressive average precision of 98.8% and a high detection speed of 218.3 fps.

Deep Learning-Based Workflow for Bone Segmentation and 3D Modeling in Cone-Beam CT Orthopedic Imaging

In this study, a deep learning-based workflow designed for the segmentation and 3D modeling of bones in cone beam computed tomography (CBCT) orthopedic imaging is presented. This workflow uses a convolutional neural network (CNN), specifically a U-Net architecture, to perform precise bone segmentation even in challenging anatomical regions such as limbs, joints, and extremities, where bone boundaries are less distinct and densities are highly variable. The effectiveness of the proposed workflow was evaluated by comparing the generated 3D models against those obtained through other segmentation methods, including SegNet, binary thresholding, and graph cut algorithms. The accuracy of these models was quantitatively assessed using the Jaccard index, the Dice coefficient, and the Hausdorff distance metrics. The results indicate that the U-Net-based segmentation consistently outperforms other techniques, producing more accurate and reliable 3D bone models. The user interface developed for this workflow facilitates intuitive visualization and manipulation of the 3D models, enhancing the usability and effectiveness of the segmentation process in both clinical and research settings. The findings suggest that the proposed deep learning-based workflow holds significant potential for improving the accuracy of bone segmentation and the quality of 3D models derived from CBCT scans, contributing to better diagnostic and pre-surgical planning outcomes in orthopedic practice.