Pattern Retrieval Research Articles

Symmetry breaking and non-ergodicity in a driven-dissipative ensemble of multilevel atoms in a cavity

Dissipative light-matter systems can display emergent collective behavior. Here, we report a Z2-symmetry-breaking phase transition in a system of multilevel Rb87 atoms strongly coupled to a weakly driven two-mode optical cavity. In the symmetry-broken phase, nonergodic dynamics manifests in the emergence of multiple stationary states with disjoint basins of attraction. This feature enables the amplification of a small atomic population imbalance into a characteristic macroscopic cavity transmission signal. Our experiment does not only showcase strongly dissipative atom-cavity systems as platforms for probing nontrivial collective many-body phenomena, but also highlights their potential for hosting technological applications in the context of sensing, density classification, and pattern retrieval dynamics within associative memories. Published by the American Physical Society 2024

Interpretable Representation and Customizable Retrieval of Traffic Congestion Patterns Using Causal Graph-Based Feature Associations

The substantial increase in traffic data offers new opportunities to inspect traffic congestion dynamics from different perspectives. This paper presents a novel framework for the interpretable representation and customizable retrieval of traffic congestion patterns using causal relation graphs, which harnesses many of these opportunities. By integrating domain knowledge with innovative data management techniques, we address the challenges of effectively handling and retrieving the growing volume of traffic data for diverse analytical purposes. The framework leverages causal graphs to encode traffic congestion patterns, capturing fundamental phenomena and their spatiotemporal relationships, thus facilitating an interpretable high-level view of traffic dynamics. Moreover, a customizable similarity measurement function is introduced based on inexact graph matching, allowing users to tailor the retrieval process to specific requirements. This framework’s capability to retrieve customizable and interpretable congestion patterns is demonstrated through extensive experiments with real-world highway traffic data in the Netherlands, highlighting its value in supporting diverse data-driven studies and applications.

Design and Implementation of a Self-Supervised Algorithm for Vein Structural Patterns Analysis Using Advanced Unsupervised Techniques

Compared to other identity verification systems applications, vein patterns have the lowest potential for being used fraudulently. The present research examines the practicability of gathering vascular data from NIR images of veins. In this study, we propose a self-supervision learning algorithm that envisions an automated process to retrieve vascular patterns computationally using unsupervised approaches. This new self-learning algorithm sorts the vascular patterns into clusters and then uses 2D image data to recuperate the extracted vascular patterns linked to NIR templates. Our work incorporates multi-scale filtering followed by multi-scale feature extraction, recognition, identification, and matching. We design the ORC, GPO, and RDM algorithms with these inclusions and finally develop the vascular pattern mining model to visualize the computational retrieval of vascular patterns from NIR imageries. As a result, the developed self-supervised learning algorithm shows a 96.7% accuracy rate utilizing appropriate image quality assessment parameters. In our work, we also contend that we provide strategies that are both theoretically sound and practically efficient for concerns such as how many clusters should be used for specific tasks, which clustering technique should be used, how to set the threshold for single linkage algorithms, and how much data should be excluded as outliers. Consequently, we aim to circumvent Kleinberg’s impossibility while attaining significant clustering to develop a self-supervised learning algorithm using unsupervised methodologies.

Investigating the discrimination ability of 3D convolutional neural networks applied to altered brain MRI parametric maps

Convolutional neural networks (CNNs) are gradually being recognized in the neuroimaging community as a powerful tool for image analysis. Despite their outstanding performances, some aspects of CNN functioning are still not fully understood by human operators. We postulated that the interpretability of CNNs applied to neuroimaging data could be improved by investigating their behavior when they are fed data with known characteristics. We analyzed the ability of 3D CNNs to discriminate between original and altered whole-brain parametric maps derived from diffusion-weighted magnetic resonance imaging. The alteration consisted in linearly changing the voxel intensity of either one (monoregion) or two (biregion) anatomical regions in each brain volume, but without mimicking any neuropathology. Performing ten-fold cross-validation and using a hold-out set for testing, we assessed the CNNs’ discrimination ability according to the intensity of the altered regions, comparing the latter’s size and relative position. Monoregion CNNs showed that the larger the modified region, the smaller the intensity increase needed to achieve good performances. Biregion CNNs systematically outperformed monoregion CNNs, but could only detect one of the two target regions when tested on the corresponding monoregion images. Exploiting prior information on training data allowed for a better understanding of CNN behavior, especially when altered regions were combined. This can inform about the complexity of CNN pattern retrieval and elucidate misclassified examples, particularly relevant for pathological data. The proposed analytical approach may serve to gain insights into CNN behavior and guide the design of enhanced detection systems exploiting our prior knowledge.

Binary pattern retrieval with Kuramoto-type oscillators via a least orthogonal lift of three patterns

Abstract Given a set of standard binary patterns and a defective pattern, the pattern retrieval task is to find the closest pattern to the defective one among these standard patterns. The Hebbian network of Kuramoto oscillators with second-order coupling provides a dynamical model for this task, and the mutual orthogonality in memorised patterns enables us to distinguish these memorised patterns from most others in terms of stability. For the sake of error-free retrieval for general problems lacking orthogonality, a unified approach was proposed which transforms the problem into a series of subproblems with orthogonality using the orthogonal lift for two patterns. In this work, we propose the least orthogonal lift for three patterns, which evidently reduces the time of solving subproblems and even the dimensions of subproblems. Furthermore, we provide an estimate for the critical strength for stability/instability of binary patterns, which is convenient in practical use. Simulation results are presented to illustrate the effectiveness of the proposed approach.

A Novel and Efficient Spatio-Temporal Co-location Pattern Mining Algorithm

Colocation pattern mining approaches aim at discovering neighboring relationships of distinct spatial features in geographic and temporal space.With big spatio-temporal dataset, there is large number of patterns often discovered. Then it is of importance to discover meaningful and patterns of interest which come as an aid in applications in use for humans and commercial use. To discover interesting patterns, we present in this article a co-location pattern mining algorithmic framework by considering neighbourhood, clustering, hashing, and mining methods. Neighbourhood relationship describes the closeness between the entities. The results of neighbourhood could be varied by varying the distance threshold. These objects exhibiting neighbouring entities are grouped using clustering technique. Clustering is a classical research approach that produces grouping of the entities. A clustering technique has been presented in the paper for spatio-temporal dimension that offers the advantage of faster grouping based on the neighbourhood relationship. Finally, a hash structure is utilized for faster access and retrieval of patterns. The proposed mining algorithm along with the distance and time threshold efficiently discovers the interesting spatio-temporal patterns and validates the patterns. The experiment conducted shows that the proposed co-location algorithm method yields effective and efficient outcome.

A coupled neural field model for the standard consolidation theory

The standard consolidation theory states that short-term memories located in the hippocampus enable the consolidation of long-term memories in the neocortex. In other words, the neocortex slowly learns long-term memories with a transient support of the hippocampus that quickly learns unstable memories. However, it is not clear yet what could be the neurobiological mechanisms underlying these differences in learning rates and memory time-scales. Here, we propose a novel modeling approach of the standard consolidation theory, that focuses on its potential neurobiological mechanisms. In addition to synaptic plasticity and spike frequency adaptation, our model incorporates adult neurogenesis in the dentate gyrus as well as the difference in size between the neocortex and the hippocampus, that we associate with distance-dependent synaptic plasticity. We also take into account the interconnected spatial structure of the involved brain areas, by incorporating the above neurobiological mechanisms in a coupled neural field framework, where each area is represented by a separate neural field with intra- and inter-area connections. To our knowledge, this is the first attempt to apply neural fields to this process. Using numerical simulations and mathematical analysis, we explore the short-term and long-term dynamics of the model upon alternance of phases of hippocampal replay and retrieval cue of an external input. This external input is encodable as a memory pattern in the form of a multiple bump attractor pattern in the individual neural fields. In the model, hippocampal memory patterns become encoded first, before neocortical ones, because of the smaller distances between the bumps of the hippocampal memory patterns. As a result, retrieval of the input pattern in the neocortex at short time-scales necessitates the additional input delivered by the memory pattern of the hippocampus. Neocortical memory patterns progressively consolidate at longer times, up to a point where their retrieval does not need the support of the hippocampus anymore. At longer times, perturbation of the hippocampal neural fields by neurogenesis erases the hippocampus pattern, leading to a final state where the memory pattern is exclusively evoked in the neocortex. Therefore, the dynamics of our model successfully reproduces the main features of the standard consolidation theory. This suggests that neurogenesis in the hippocampus and distance-dependent synaptic plasticity coupled to synaptic depression and spike frequency adaptation, are indeed critical neurobiological processes in memory consolidation.

Replica symmetry breaking in supervised and unsupervised Hebbian networks

Abstract Hebbian neural networks with multi-node interactions, often called Dense Associative Memories, have recently attracted considerable interest in the statistical mechanics community, as they have been shown to outperform their pairwise counterparts in a number of features, including resilience against adversarial attacks, pattern retrieval with extremely weak signals and supra-linear storage capacities. However, their analysis has so far been carried out within a replica-symmetric theory. In this manuscript, we relax the assumption of replica symmetry and analyse these systems at one step of replica-symmetry breaking, focusing on two different prescriptions for the interactions that we will refer to as supervised and unsupervised learning. We derive the phase diagram of the model using two different approaches, namely Parisi's hierarchical ansatz for the relationship between different replicas within the replica approach, and the so-called telescope ansatz within Guerra's interpolation method: our results show that replica-symmetry breaking does not alter the threshold for learning and slightly increases the maximal storage capacity. Further, we also derive analytically the instability line of the replica-symmetric theory, using a generalization of the De Almeida and Thouless approach.

Fracture density reconstruction using direct sampling multiple-point statistics and extreme value theory

The aim of this work is to present a methodology for the reconstruction of missing fracture density within highly fractured intervals, which can represent preferential fluid flow pathways. The lack of record can be very common due to the intense presence of fractures, dissolution processes, or data acquisition issues. The superposition of numerous fractures makes the definition of fracture surfaces impossible, as a consequence, modeling such zones is challenging. In order to address this issue, the usage of direct sampling multiple-point statistics to perform gap filling in well logs is demonstrated as an alternative to other techniques. It reproduces data patterns and provides several models representing uncertainty. The method was tested in intervals from a highly fractured well, by removing previously known fracture density data, and simulating different scenarios with direct sampling. Simulation results are compared to the observed data using cross-validation and continuous rank probability score. The reference scenario training data set consists in one well and two variables: fracture density and fracture occurrence. A sensitivity analysis is carried out considering additional variables, additional wells, different intervals, resampling with extremes, and other gap filling techniques. The auxiliary variable plays an important role in pattern matching, but adding wells and logs increases the complexity of the method without improving pattern retrieval. Best results are obtained applying extreme values theory for stochastic process with the enrichment of the fracture density data at the tail region, followed by resampling of the new values. The enriched data is used for the gap filling resulting in lower continuous rank probability score, and the achievement of extreme fracture density values.

Exponential Capacity of Dense Associative Memories.

Recent generalizations of the Hopfield model of associative memories are able to store a number P of random patterns that grows exponentially with the number N of neurons, P=exp(αN). Besides the huge storage capacity, another interesting feature of these networks is their connection to the attention mechanism which is part of the Transformer architecture widely applied in deep learning. In this work, we study a generic family of pattern ensembles using a statistical mechanics analysis which gives exact asymptotic thresholds for the retrieval of a typical pattern, α_{1}, and lower bounds for the maximum of the load α for which all patterns can be retrieved, α_{c}, as well as sizes of attraction basins. We discuss in detail the cases of Gaussian and spherical patterns, and show that they display rich and qualitatively different phase diagrams.

Image Hash Layer Triggered CNN Framework for Wafer Map Failure Pattern Retrieval and Classification

Recently, deep learning methods are often used in wafer map failure pattern classification. CNN requires less feature engineering but still needs preprocessing, e.g., denoising and resizing. Denoising is used to improve the quality of the input data, and resizing is used to transform the input into an identical size when the input data sizes are various. However, denoising and resizing may distort the original data information. Nevertheless, CNN-based applications are focusing on studying different feature map architectures and the input data manipulation is less attractive. In this study, we proposed an image hash layer triggered CNN framework for wafer map failure pattern retrieval and classification. The motivation and novelty are to design a CNN layer that can play as a resizing, information retrieval-preservation method in one step. The experiments proved that the proposed hash layer can retrieve the failure pattern information while maintaining the classification performance even though the input data size is decreased significantly. In the meantime, it can prevent overfitting, false negatives, and false positives, and save computing costs to a certain extent.

Active oscillatory associative memory

Traditionally, physical models of associative memory assume conditions of equilibrium. Here, we consider a prototypical oscillator model of associative memory and study how active noise sources that drive the system out of equilibrium, as well as nonlinearities in the interactions between the oscillators, affect the associative memory properties of the system. Our simulations show that pattern retrieval under active noise is more robust to the number of learned patterns and noise intensity than under passive noise. To understand this phenomenon, we analytically derive an effective energy correction due to the temporal correlations of active noise in the limit of short correlation decay time. We find that active noise deepens the energy wells corresponding to the patterns by strengthening the oscillator couplings, where the more nonlinear interactions are preferentially enhanced. Using replica theory, we demonstrate qualitative agreement between this effective picture and the retrieval simulations. Our work suggests that the nonlinearity in the oscillator couplings can improve memory under nonequilibrium conditions.

A Multimedia based Patterns Retrieval from Database Patterns and Storing

A Multimedia based Patterns Retrieval from Database Patterns and Storing

Efficient Retrieval of Images with Irregular Patterns Using Morphological Image Analysis: Applications to Industrial and Healthcare Datasets.

Image retrieval is the process of searching and retrieving images from a datastore based on their visual content and features. Recently, much attention has been directed towards the retrieval of irregular patterns within industrial or healthcare images by extracting features from the images, such as deep features, colour-based features, shape-based features, and local features. This has applications across a spectrum of industries, including fault inspection, disease diagnosis, and maintenance prediction. This paper proposes an image retrieval framework to search for images containing similar irregular patterns by extracting a set of morphological features (DefChars) from images. The datasets employed in this paper contain wind turbine blade images with defects, chest computerised tomography scans with COVID-19 infections, heatsink images with defects, and lake ice images. The proposed framework was evaluated with different feature extraction methods (DefChars, resized raw image, local binary pattern, and scale-invariant feature transforms) and distance metrics to determine the most efficient parameters in terms of retrieval performance across datasets. The retrieval results show that the proposed framework using the DefChars and the Manhattan distance metric achieves a mean average precision of 80% and a low standard deviation of ±0.09 across classes of irregular patterns, outperforming alternative feature-metric combinations across all datasets. Our proposed ImR framework performed better (by 8.71%) than Super Global, a state-of-the-art deep-learning-based image retrieval approach across all datasets.

Unified approach for applications of oscillatory associative-memory networks with error-free retrieval.

Given a set of standard binary patterns and a defective pattern, the binary pattern retrieval task is to find the closest pattern to the defective one among these standard patterns. The associative-memory network of Kuramoto oscillators consisting of a Hebbian coupling term and a second-order Fourier term can be applied to this task. When the memorized patterns stored in the Hebbian coupling are mutually orthogonal, recent studies show that the network is capable of distinguishing the memorized patterns from most other patterns. However, the orthogonality usually fails in real situations. In this paper, we present a unified approach for the application of this model in pattern retrieval problems with any general set of standard patterns. By subgrouping the standard patterns and employing an orthogonal lift of each subgroup, this approach makes use of the theory in the case of mutually orthogonal memorized patterns. In particular, the error-free retrieval can be guaranteed, which requires that the retrieved pattern must coincide with one of the standard patterns. As illustrative simulations, pattern retrieval tests for partly sheltered Arabic number symbols are presented.

Study on chemical constituents and fingerprints of Phellodendron amurense Rupr. based on ultra-performance liquid chromatography-quadrupole-time-of-flight-mass spectrometry.

The chemical constituents from Phellodendron amurense Rupr. were characterized systematically by ultra-performance liquid chromatography-quadrupole-time-of-flight-mass spectrometry method for collecting mass spectrometry data, and the fingerprints method was established, providing reference for its quality control. The chromatographic column was ACQUITY UPLC BEH-C18 (100mm×2.1mm, 1.7μm). The mobile phase was acetonitrile-0.1% formic acid aqueous solution and the compounds from P. amurense Rupr. were identified by Qualitative Analysis 10.0 software, reference substance, retention time, mass spectrometry fragmentation pattern and database retrieval. Meanwhile, liquid chromatography-mass spectrometry fingerprint methods of P. amurense Rupr. and Phellodendron chinense Schneid. were established by using the similarity evaluation system of chromatographic fingerprint of traditional Chinese medicine (2012 edition), and the differences were analyzed by multivariate statistical analysis methods. A total of 105 compounds were identified, including 102 alkaloids, two phenolic acids, and one lactone compound. Liquid chromatography-mass spectrometry fingerprint method was established with ideal precision, stability and repeatability, and 12 quality differential markers were recognized between the above two herbs. Liquid chromatography-mass spectrometry method can be used for qualitative analysis of the constituents of Phellodendron amurense Rupr., providing reference for clarifying the material basis and promoting the clinical precision medication and quality evaluation of P. amurense Rupr.

Batik Nitik 960 Dataset for Classification, Retrieval, and Generator

Batik is one of the traditional heritages of Indonesia, with each motif of batik having a profound cultural and philosophical significance. This article introduces Batik Nitik 960 dataset from Yogyakarta, Indonesia. The dataset was extracted from a piece of fabric with 60 Nitik patterns. The dataset was supplied by the Paguyuban Pecinta Batik Indonesia (PPBI) Sekar Jagad Yogyakarta collection of Winotosasto Batik and the data were extracted from the APIPS Gallery. Each of the 60 categories in the collection contains 16 photographs, for a total of 960 images. The photographs were acquired with a Sony Alpha a6400, illuminated with a Godox SK II 400, and the data were compressed using the jpg file format. Each category contains four motifs rotated by 90, 180, and 270 degrees. Thus, the total number of images per motif is 16. Each class has a specific philosophical significance associated with the motif’s origins. This dataset aims to enable the training and evaluation of machine learning models for classification, retrieval, or generation of a new batik pattern using a generative adversarial network. To our knowledge, this study is the first to present a Batik Nitik dataset equipped with philosophical significance that is freely accessible.

SAXRegEx: Multivariate time series pattern search with symbolic representation, regular expression, and query expansion

We present SAXRegEx, a method for pattern search in multivariate time series in the presence of various distortions, such as duration variation, warping, and time delay between signals. For example, in the automotive industry, calibration engineers spontaneously search for event-induced patterns in new measurements under time pressure. Current methods do not sufficiently address duration (horizontal along the time axis) scaling and inter-track time delay. One reason is that it can be overwhelmingly complex to consider scaling and warping jointly and analyze temporal dynamics and attribute interrelation simultaneously. SAXRegEx meets this challenge with a novel symbolic representation adapted to handle time series with multiple tracks. We employ methods from text retrieval, i.e., regular expression matching, to perform a pattern retrieval and develop a novel query expansion algorithm to deal flexibly with pattern distortions. Experiments show the effectiveness of our approach, especially in the presence of such distortions, and its efficiency surpassing the benchmarking methods. We have developed a user interface with the emphasis on multivariate query definition with inter-track time shifts and algorithm parameter setting. While we design the method primarily for automotive data, it is well transferable to other domains.

Neural computing with coherent laser networks

Abstract We show that coherent laser networks (CLNs) exhibit emergent neural computing capabilities. The proposed scheme is built on harnessing the collective behavior of laser networks for storing a number of phase patterns as stable fixed points of the governing dynamical equations and retrieving such patterns through proper excitation conditions, thus exhibiting an associative memory property. It is discussed that despite the large storage capacity of the network, the large overlap between fixed-point patterns effectively limits pattern retrieval to only two images. Next, we show that this restriction can be uplifted by using nonreciprocal coupling between lasers and this allows for utilizing a large storage capacity. This work opens new possibilities for neural computation with coherent laser networks as novel analog processors. In addition, the underlying dynamical model discussed here suggests a novel energy-based recurrent neural network that handles continuous data as opposed to Hopfield networks and Boltzmann machines that are intrinsically binary systems.

OCTOPOD: single-bunch tomography for angular-spectral characterization of laser-driven protons

Abstract Laser–plasma accelerated (LPA) proton bunches are now applied for research fields ranging from ultra-high-dose-rate radiobiology to material science. Yet, the capabilities to characterize the spectrally and angularly broad LPA bunches lag behind the rapidly evolving applications. The OCTOPOD translates the angularly resolved spectral characterization of LPA proton bunches into the spatially resolved detection of the volumetric dose distribution deposited in a liquid scintillator. Up to 24 multi-pinhole arrays record projections of the scintillation light distribution and allow for tomographic reconstruction of the volumetric dose deposition pattern, from which proton spectra may be retrieved. Applying the OCTOPOD at a cyclotron, we show the reliable retrieval of various spatial dose deposition patterns and detector sensitivity over a broad dose range. Moreover, the OCTOPOD was installed at an LPA proton source, providing real-time data on proton acceleration performance and attesting the system optimal performance in the harsh laser–plasma environment.