Similar Pattern Recognition Research Articles

A novel framework for generic Spark workload characterization and similar pattern recognition using machine learning

Comprehensive workload characterization plays a pivotal role in comprehending Spark applications, as it enables the analysis of diverse aspects and behaviors. This understanding is indispensable for devising downstream tuning objectives, such as performance improvement. To address this pivotal issue, our work introduces a novel and scalable framework for generic Spark workload characterization, complemented by consistent geometric measurements. The presented approach aims to build robust workload descriptors by profiling only quantitative metrics at the application task-level, in a non-intrusive manner. We expand our framework for downstream workload pattern recognition by incorporating unsupervised machine learning techniques: clustering algorithms and feature selection. These techniques significantly improve the process of grouping similar workloads without relying on predefined labels. We effectively recognize 24 representative Spark workloads from diverse domains, including SQL, machine learning, web search, graph, and micro-benchmarks, available in HiBench. Our framework achieves a high accuracy F-Measure score of up to 90.9% and a Normalized Mutual Information of up to 94.5% in similar workload pattern recognition. These scores significantly outperform the results obtained in a comparative analysis with an established workload characterization approach in the literature.

Evaluation of Human Perception Thresholds Using Knowledge-Based Pattern Recognition

This paper presents research on determining individual perceptual thresholds in cognitive analyses and the understanding of visual patterns. Such techniques are based on the processes of cognitive resonance and can be applied to the division and reconstruction of images using threshold algorithms. The research presented here considers the most important parameters that affect the determination of visual perception thresholds. These parameters are the thematic knowledge and personal expectations that arise at the time of image observation and recognition. The determination of perceptual thresholds has been carried out using visual pattern splitting techniques through threshold methods. The reconstruction of the divided patterns was carried out by combining successive components that, as information was gathered, allowed more and more details to become apparent in the image until the observer could recognize it correctly. The study being carried out in this way made it possible to determine individual perceptual thresholds for dozens of test subjects. The results of the study also showed strong correlations between the determined perceptual thresholds and the participants’ accumulated thematic knowledge, expectations and experiences from a previous recognition of similar image patterns.

Multistate Resistive Switching with Self-Rectifying Behavior and Synaptic Characteristics in a Solution-processed ZnO/PTAA Bilayer Memristor

The progress of artificial synaptic devices is vital to the realization of the consciousness of effectual bioinspired neuromorphic computing systems. In this study, we fabricated an ITO/ZnO/PTAA/Ag artificial synaptic memristor based on a low-cost solution process. The fabricated device exhibited uniform gradual bipolar resistive switching with excellent endurance and self-rectifying behavior owing to the bilayer heterojunction structure of ZnO/PTAA. The growth of the conducting filament can be efficiently controlled by modulating the current compliance and voltage during the SET process. Modification of conductance states was also observed by simulations to stimuli, which are essential for synaptic function in neuromorphic computing. Various pulse measurements were performed to mimic synaptic behaviors, including long-term potentiation, long-term depression, spike-rate-dependent plasticity, paired-pulse facilitation, and post-tetanic potentiation. Moreover, we reveal that the real device shows an approximately similar pattern recognition rate as the ideal device owing to a more uniform conductance update.

Position statement on classification of basal cell carcinomas. Part 1: unsupervised clustering of experts as a way to build an operational classification of advanced basal cell carcinoma based on pattern recognition.

BackgroundNo simple classification system has emerged for ‘advanced basal cell carcinomas’, and more generally for all difficult‐to‐treat BCCs (DTT‐BCCs), due to the heterogeneity of situations, TNM inappropriateness to BCCs, and different approaches of different specialists.ObjectiveTo generate an operational classification, using the unconscious ability of experts to simplify the great heterogeneity of the clinical situations into a few relevant groups, which drive their treatment decisions.MethodNon‐supervised independent and blinded clustering of real clinical cases of DTT‐BCCs was used. Fourteen international experts from different specialties independently partitioned 199 patient cases considered ‘difficult to treat’ into as many clusters they want (≤10), choosing their own criteria for partitioning. Convergences and divergences between the individual partitions were analyzed using the similarity matrix, K‐mean approach, and average silhouette method.ResultsThere was a rather consensual clustering of cases, regardless of the specialty and nationality of the experts. Mathematical analysis showed that consensus between experts was best represented by a partition of DTT‐BCCs into five clusters, easily recognized a posteriori as five clear‐cut patterns of clinical situations. The concept of ‘locally advanced’ did not appear consistent between experts.ConclusionAlthough convergence between experts was not granted, this experiment shows that clinicians dealing with BCCs all tend to work by a similar pattern recognition based on the overall analysis of the situation. This study thus provides the first consensual classification of DTT‐BCCs. This experimental approach using mathematical analysis of independent and blinded clustering of cases by experts can probably be applied to many other situations in dermatology and oncology.

Employing Drug Delivery Strategies to Overcome Challenges Using TLR7/8 Agonists for Cancer Immunotherapy.

Toll-like receptors (TLRs) are a potential target for cancer immunotherapy due to their role in the activation of the innate immune system. More specifically, TLR7 and TLR8, two structurally similar pattern recognition receptors that trigger interferon and cytokine responses, have proven to be therapeutically relevant targets for cancer in numerous preclinical and clinical studies. When triggered by an agonist, such as imiquimod or resiquimod, the TLR7/8 activation pathway induces cellular and humoral immune responses that can kill cancer cells with high specificity. Unfortunately, TLR7/8 agonists also present a number of issues that must be overcome prior to broad clinical implementation, such as poor drug solubility and systemic toxic effects. To overcome the key limitations of TLR7/8 agonists as a cancer therapy, biomaterial-based drug delivery systems have been developed. These delivery devices are highly diverse in their design and include systems that can be directly administered to the tumor, passively accumulated in relevant cancerous and lymph tissues, triggered by environmental stimuli, or actively targeted to specific physiological areas and cellular populations. In addition to improved delivery systems, recent studies have also demonstrated the potential benefits of TLR7/8 agonist co-delivery with other types of therapies, particularly checkpoint inhibitors, cancer vaccines, and chemotherapeutics, which can yield impressive anti-cancer effects. In this review, we discuss recent advances in the development of TLR7/8 agonist delivery systems and provide perspective on promising future directions.

Context-Adaptive Sub-Nyquist Sampling for Low-Power Wearable Sensing Systems

This paper investigates a context-adaptive sample acquisition strategy at sub-Nyquist sampling rate for wearable embedded sensor devices. Our approach can be applied to compressive sensing frameworks to minimise sampling and transmission costs. We consider a context estimate to represent the local signal structure and a feed-forward response model to continuously tune signal acquisition of an online sampling and transmission system. To evaluate our approach, we analysed the performance in different pattern recognition scenarios. We report three case studies here: (1) eating monitoring based on electromyography measurements in smart eyeglasses, (2) human activity recognition based on waist-worn inertial sensor data, and (3) heartbeat detection and arrhythmia classification based on single-lead electrocardiogram readings. Compared to conventional sub-Nyquist sampling, our context-adaptive approach saves between 13 to 22 percent of energy, while achieving similar pattern recognition performance and reconstruction error.

The use of ash at Late Lower Paleolithic Qesem Cave, Israel-An integrated study of use-wear and residue analysis.

Employing an integrated approach to investigate the use of Late Lower Paleolithic flint tools found at the site of Qesem Cave (Israel), we revealed a particular trace pattern related to the employment of ashes at the site. Using a designated collection of replica items and combining use-wear and residue (morphological analysis, FTIR, SEM-EDX) analyses, we revealed the intentional use of ashes in preserving foods for delayed consumption as well as hide for delayed processing. Our interpretation, we believe is the most plausible one since we were able to delineate the specific use-wear fingerprints of the intentional use of ashes for such purposes, suggesting that our approach might be useful for the recognition of other similar functional-behavioral patterns. Lastly, in support of previous findings at Qesem Cave, our current findings present evidence for the processing of organic matters intentionally mixed with ash, leading us to suggest that the inhabitants of Qesem Cave were proficient not only in the habitual use of fire but also of its main by-product, ash. Hence, we call for a reassessment of the timeline currently assigned to hominins’ utilization of ash for storing and processing vegetal foods and hide.

Massively Distributed Graph Distances

Graph distance (or similarity) scores are used in several graph mining tasks, including anomaly detection, nearest neighbor and similarity search, pattern recognition, transfer learning, and clustering. Graph distances that are metrics and, in particular, satisfy the triangle inequality, have theoretical and empirical advantages. Well-known graph distances that are metrics include the chemical or the Chartrand-Kubiki-Shultz (CKS) distances. Unfortunately, both are computationally intractable. Recent efforts propose using convex relaxations of the chemical and CKS distances. Though distance computation becomes a convex optimization problem under these relaxations, the number of variables is quadratic in the graph size; this makes traditional optimization algorithms prohibitive even for small graphs. We propose a distributed method for massively parallelizing this problem using the Alternating Directions Method of Multipliers (ADMM). Our solution uses a novel, distributed bisection algorithm for computing a $p$ -norm proximal operator as a building block. We demonstrate its scalability by conducting experiments over multiple parallel environments.

Identification of variety of rice and determination of content of each rice in mixtures of two rices by nonlinear chemical analysis

Fingerprints of two varieties of rice and their mixtures were investigated by a nonlinear chemical reaction system consisting of rice components, sodium bromate, manganese sulfate, sulfuric acid and acetone. The variety of rice was identified by the visual characteristic of fingerprint and system similarity pattern recognition, and the content of each variety of rice in the mixture was determined by the quantitative information of fingerprint. The results show that nonlinear chemical analysis may be used to exactly identify the variety of pure rice and to accurately determine the content of each variety of rice in the mixture, indicating the method is simple and convenient.

Study of Dynamometer Cards Identification Based on Root-Mean-Square Error Algorithm

The surface dynamometer cards are important working condition data of sucker-rod pumping system. It has a very important practical significance for the analysis of transmission system and the diagnosis of oil production condition of sucker-rod pumping system. The pump dynamometer cards are important reference for the diagnosis of oil production condition, and its key technology is the identification of pump dynamometer cards. A new similar pattern recognition algorithm based on root-mean-square error (RMSE) is proposed, a theoretical model of the similarity matching algorithm based on RMSE is established, and the algorithm is studied and analyzed. The three-dimensional vibration mathematical models for the surface dynamometer cards are created, by which the surface dynamometer cards can be transformed to the pump dynamometer cards. The accuracy, reliability and stability between the algorithm of RMSE similarity matching and the classical algorithms of similarity pattern matching are studied. The research shows that the resistance to the graphics deformation of RMSE algorithm is the highest among all algorithms. The application of RMSE algorithm and classic similarity matching algorithms to the identification of real pump dynamometer cards and the fault diagnosis of oil wells indicates that the RMSE algorithm has very high identification reliability and accuracy. The remarkable feature of the RMSE algorithm is that it has very high identification accuracy for small difference, while the classical similarity matching algorithms do not have this feature.

Pattern recognition for electroencephalographic signals based on continuous neural networks

This study reports the design and implementation of a pattern recognition algorithm to classify electroencephalographic (EEG) signals based on artificial neural networks (NN) described by ordinary differential equations (ODEs). The training method for this kind of continuous NN (CNN) was developed according to the Lyapunov theory stability analysis. A parallel structure with fixed weights was proposed to perform the classification stage. The pattern recognition efficiency was validated by two methods, a generalization–regularization and a k-fold cross validation (k=5). The classifier was applied on two different databases. The first one was made up by signals collected from patients suffering of epilepsy and it is divided in five different classes. The second database was made up by 90 single EEG trials, divided in three classes. Each class corresponds to a different visual evoked potential. The pattern recognition algorithm achieved a maximum correct classification percentage of 97.2% using the information of the entire database. This value was similar to some results previously reported when this database was used for testing pattern classification. However, these results were obtained when only two classes were considered for the testing. The result reported in this study used the whole set of signals (five different classes). In comparison with similar pattern recognition methods that even considered less number of classes, the proposed CNN proved to achieve the same or even better correct classification results.

The sedimentation of Suminagashi-like floating clay patterns at El Chichón crater lake (Chiapas, Mexico)

Abstract This study describes the traditional Japanese Suminagashi paper marbling technique in an unusual, non-artistic way based on observations in nature (El Chichón crater lake, Chiapas, Mexico) and supported by physical processes such as wave action and Marangoni flow. It is the first time that these seemingly unrelated phenomena are linked. We show how clays floating on the surface of the El Chichón crater lake bear a strong resemblance to Suminagashi patterns. Clays rise from the lake bottom by vigorous bubbling of gases or thermal convection. After floating on the water surface due to capillary forces, the clays are transported towards the lake shore by wind-generated waves. The clay-covered lake surface is subject to Marangoni flow when the lake becomes very shallow (a few centimetres) near the lake shore. The flat lake bottom and the dynamic alternation between retreat and incurrence of the lake shore consequently result in the precipitation of the clay patterns, preserving the Suminagashi-like designs in the lake sediments. Recognition of similar patterns in the sedimentary record could indicate the presence of a shallow sedimentary environment in the past, possibly pointing to a heated crater lake.

Application of Fourier transform to preprocessing chromatographic fingerprints of traditional Chinese medicine

Retention time shift is a significant impediment against analyzing chromatographic fingerprints of Traditional Chinese Medicine (TCM) with similarity estimation and pattern recognition methods. This work aims at developing a fingerprint preprocessing method that can eliminate the negative effect of retention time shift on similarity estimation and pattern recognition analysis in the quality evaluation of TCM. Both simulated chromatograms and experimental chromatographic fingerprints of Radix Puerariae thomsonii (RPT) were investigated in order to evaluate the practicality of the proposed method. Fourier transform (FT) was used to process these chromatographic signals. The magnitude data of these signals were calculated. In the obtained magnitude data, the negative effect of retention time shift was successfully excluded. Thus, the quality of the investigated RPT samples can be correctly evaluated by using the magnitude data as the input variables of similarity estimation and pattern recognition analysis. It is demonstrated that FT is a practicable and promising method for preprocessing chromatographic fingerprints of TCM prior to similarity estimation and pattern recognition analysis.

On the Mitchell similarity measure and its application to pattern recognition

This paper is a response to the similarity measure and pattern recognition problem of Mitchell that was published in Pattern Recognition Letters, 2003. The purpose of this paper is threefold. First, we reviewed and revised her computation for similarity measures. Second, we proved that the similarity values for the one-norm should be larger than that for the two-norm for her pattern recognition problem. Third, we proposed a more scattered similarity measure to help researchers determine patterns. Our findings may shed light on the ongoing debate between Li and Cheng (2002) and Mitchell (2003).

Literature Survey On Clustering Techniques

Clustering is the assignment of data objects (records) into groups (called clusters) so that data objects from the same cluster are more similar to each other than objects from different clusters. Clustering techniques have been discussed extensively in similarity search, Segmentation, Statistics ,Machine Learning ,Trend Analysis, Pattern Recognition and classification. Clustering methods can be classified in to i)partition methods2)Hierarchical methods,3)Density Based methods 4)Grid based methods5)Model Based methods. in this paper, i would like to give review about clustering methods by taking some example for each classification. I am also providing comparative statement by taking constraints i.e Data type, Cluster Shape, Complexity, Data Set, Measure, Advantages and Disadvantages. Keywords: clustering; Partition, Hierarchical, Density, grid, Model

A SIMPLE PATTERN RECOGNITION APPROACH FOR MONITORING INCIPIENT STATOR FAULTS IN SALIENT-POLE SYNCHRONOUS GENERATORS

This paper studies the efiect of incipient stator faults in salient-pole synchronous generators and its detection using a simple pattern recognition methodology. A theoretical linear model for the synchronous generator is flrst developed to provide the relationships between stator and rotor harmonic currents and possible incipient faults on stator electric circuits. All theoretical flndings were verifled by experimental results. The stator currents and its fifl and dq representations have been used to detect incipient faults on salient-pole synchronous generators using a similar pattern recognition technique which have been proposed for induction machines. From our test results, it became clear that the proposed methodology is capable of correctly monitoring incipient stator faults in salient-pole synchronous generators.

Optimised search strategies to improve structural pattern recognition techniques

Data retrieval methods are based on three essential aspects: feature extraction (to reduce signal dimensionality), the classification system (to index objects according to some criteria) and similarity measures (to compare how similar two objects are); but there is not a single solution to handle these key elements. This paper provides a new solution to the localisation and extraction of similar patterns in time-series data. Alternative searches are proposed to objectively increase the recognition of similar patterns so as to achieve better results on the data retrieval. These search strategies have been studied with excellent results in the detection of long subpatterns. Long subpatterns are not very easy to identify since even a single mismatch in one character can compromise similarity between two patterns. Identifying long patterns in a fast, fault-tolerant and intelligent way is the aim of the analysed strategies, which are formally based on statistical criteria and some aspects of probability theory.

The molecular and cellular basis of infection—Perspectives from the first advanced summer school in Africa

The molecular and cellular basis of infection—Perspectives from the first advanced summer school in Africa

Evaluation of thermographic imaging of the limbs of healthy dogs

To describe a thermographic imaging protocol, identify normal thermographic patterns (ie, color map reflecting the skin temperature distribution) for various regions of interest (ROIs) of dog limbs, and evaluate effects of clipping the coat on thermographic patterns and limb temperature in healthy dogs. 10 healthy dogs. Each dog was thermographically evaluated in the same room (ambient temperature, 21 degrees C) via ROIs that included cranial and caudal views of the body, full lateral body views, full views of the limbs, and views of various limb regions. After initial imaging, the coat was clipped on the forelimbs and hind limbs only. Each dog was then evaluated 15 and 60 minutes and 24 hours after clipping by use of the same protocol. For each ROI within a category (intact coat and each time point after clipping), mean temperatures were similar among the 10 dogs. Pairwise comparisons for 15 and 60 minutes and 24 hours established patterns of temperature stabilization among the 3 time points. Temperatures did not differ significantly between the left and right limbs. There was a mean success rate of 75% for use of image pattern analysis for recognition of similar thermographic patterns in the forelimbs and hind limbs. Thermography can be a viable, noninvasive imaging modality that provides consistent images with reproducible thermal patterns in ROIs examined in healthy dogs. Although the coat had a predictable influence to decrease the mean temperature, thermal patterns remained fairly consistent after the coat was clipped.

1535 カルバック識別情報量を用いた設備診断 : 相関関数法との比較

This paper concerns on detection and classification of machinery conditions by the application of patter recognition. In previous paper, the Kullback discrimination information with AR model has been applied to detect the pre-assumed conditions of a compressor, (1) normal, (2) suction filter choking, (3) suction valve spring failure, (4) piston ring wear, (5) suction valve failure and combination of (2)-(5). This method could classify these conditions. In this paper, this method is compared with another similar pattern recognition method, correlation function method, from the point of anti-noise characteristics.