Artificial Pattern Research Articles

Hydrological Connectivity Evolution of Yellow River Delta Wetland Based on Hydrological Connectivity Pattern Analysis

Water is a limiting factor for the ecological protection and high-quality development of the Yellow River Delta. At present, the classification system for wetland hydrological connectivity patterns is imperfect and cannot meet practical management needs. Therefore, this paper constructs a hydrological connectivity classification index system based on three aspects—the pressure index, state index, and response index based on the “Pressure-State-Response” model and the analytic hierarchy process (AHP)—and then uses the network connectivity index to describe the dynamics of hydrological connectivity in the Yellow River Delta wetland under different connectivity patterns. The results show that (1) the hydrological connectivity patterns in the Yellow River Delta can be divided into five types as follows: artificial freshwater connectivity, artificial saltwater connectivity, natural–artificial freshwater connectivity, artificial–natural saltwater connectivity, and natural freshwater–saltwater connectivity. Among these types, the artificial freshwater connectivity is the most widely distributed, accounting for approximately 55.14% of the study area, followed by the artificial saltwater connectivity (24.68%), natural saltwater connectivity (9.45%), natural–artificial freshwater connectivity (8.1%), and natural freshwater–saltwater connectivity (2.63%). (2) From 1990 to 2020, the network closure (α), line point rate (β), and network connectivity (γ) indices of the Yellow River Delta wetland decreased from 0.95, 2.85, and 0.96 to 0.75, 2.51, and 0.83, respectively, and the overall connectivity level remained at a high level. The α, β, and γ values of the artificial freshwater connectivity pattern decreased from 0.93, 2.86, and 0.95 to 0.68, 2.36, and 0.79 and became the type with the lowest connectivity. The α, β, and γ indices of the natural–artificial freshwater, artificial saltwater, natural saltwater, and natural freshwater–saltwater connectivity patterns increased. Among these patterns, the artificial saltwater connectivity increased from 0.74, 2.37, and 0.83 to 0.93, 2.80, and 0.95 and had the highest connectivity. This paper has certain value and significance for wetland hydrology management.

Efficacy and adverse reactions of fractional CO2 lasers for treating papular acne scars: a retrospective study of 35 patients.

Papular acne scars are a special type of acne scar, and the prevalence and treatment of this disease have rarely been reported in the literature; moreover, the prevalence of this disease is often neglected, and treatment is difficult. Our study revealed a high prevalence of this type of acne scar in the clinic and explored an effective and safe method. This retrospective study aimed to analyse the prevalence of papular acne scarring among patients attending our Dermatology Laser Clinic and evaluate the clinical efficacy of fractional CO2 lasers. We retrieved the data of 370 patients with acne scarring who visited our hospital between April 2021 and November 2022 and analysed the prevalence of papillary acne scarring among them. Among these patients, 35 underwent CO2 laser treatment using an artificial grid pattern. A total of three treatments were administered, with a two-month interval between each session. Scar assessment was conducted using the Global Scar Scale (GSS) and the Acne Scar Clinical Assessment (ECCA) scale, along with physician visual evaluation and patient satisfaction surveys, both before the first treatment and one month after the final treatment. Adverse reactions were recorded during follow-up visits after each treatment. Among the 370 patients with acne scarring, 128 exhibited papular acne scarring, resulting in a prevalence rate of 34.6%. Among them, 37.5% were male and 32.6% were female. A total of 90.6% of patients had combined other types of acne scarring, while 9.4% had papular acne scarring exclusively. Following CO2 laser grid treatment, there was a significant reduction in GSS scores and ECCA values, accompanied by a noticeable improvement in physician visual evaluation and patient satisfaction scores. Papular acne scarring has a relatively high incidence rate, and there is no significant sex difference. It often coexists with other types of acne scarring. CO2 laser treatment using an artificial grid pattern effectively improved papular acne scarring with a good safety profile.

LungPath: artificial intelligence-driven histologic pattern recognition for improved diagnosis of early-stage invasive lung adenocarcinoma.

Early-stage invasive lung adenocarcinoma (ADC) characterized by a predominant micropapillary or solid pattern exhibit an elevated risk of recurrence following sub-lobar resection, thus determining histological subtype of early-stage invasive ADC prior surgery is important for formulating lobectomy or sub-lobar resection. This study aims to develop a deep learning algorithm and assess its clinical capability in distinguishing high-risk or low-risk histologic patterns in early-stage invasive ADC based on preoperative computed tomography (CT) scans. Two retrospective cohorts were included: development cohort 1 and external test cohort 2, comprising patients diagnosed with T1 stage invasive ADC. Electronic medical records and CT scans of all patients were documented. Patients were stratified into two risk groups. High-risk group: comprising cases with a micropapillary component ≥5% or a predominant solid pattern. Low-risk group: encompassing cases with a micropapillary component <5% and an absence of a predominant solid pattern. The overall segmentation model was modified based on Mask Region-based Convolutional Neural Network (Mask-RCNN), and Residual Network 50 (ResNet50)_3D was employed for image classification. A total of 432 patients participated in this study, with 385 cases in cohort 1 and 47 cases in cohort 2. The fine-outline results produced by the auto-segmentation model exhibited a high level of agreement with manual segmentation by human experts, yielding a mean dice coefficient of 0.86 [95% confidence interval (CI): 0.85-0.87] in cohort 1 and 0.84 (95% CI: 0.82-0.85) in cohort 2. Furthermore, the deep learning model effectively differentiated the high-risk group from the low-risk group, achieving an area under the curve (AUC) of 0.89 (95% CI: 0.88-0.90) in cohort 1. In the external validation conducted in cohort 2, the deep learning model displayed an AUC of 0.87 (95% CI: 0.84-0.88) in distinguishing the high-risk group from the low-risk group. The average diagnostic time was 16.00±3.2 seconds, with an accuracy of 0.82 (95% CI: 0.81-0.83). We have developed a deep learning algorithm, LungPath, for the automated segmentation of pulmonary nodules and prediction of high-risk histological patterns in early-stage lung ADC based on CT scans.

Application of a quality threshold to improve liver shear wave elastography measurements in free-breathing pediatric patients.

This study assessed the benefits of quality threshold (QT) implementation for liver shear wave elastography (SWE) in children during free breathing. The QT, which adjusts the SWE map display based on shear wave quality, was set at 55%. Phantom measurements (PMs) were taken with a fixed probe using QT (termed PM-1); a moving probe without QT (PM-2); and a moving probe with QT (PM-3). Each measurement was subjected to random samplings of various sizes. Clinical measurements (CMs) were obtained from children with biliary atresia using following protocols: CM-1, manually defined regions of interest (ROIs); CM-2, default ROIs without QT; and CM-3, default ROIs with QT. Elasticity measurements were compared across fibrosis grades, and color patterns on the SWE maps were analyzed. In the phantom experiments, the moving probe produced lower elasticity measurements; this difference decreased upon QT application. With the moving probe, random sampling indicated fewer interquartile range-to-median ratios exceeding 30% upon QT application (4% vs. 14% when five values were sampled, P=0.004). In clinical experiments, QT improved the differentiation of fibrosis grade in patients over 5 years old, with a significant difference between moderate and severe fibrosis (P=0.004). Elasticity variability was positively correlated with fibrosis grade (τ=0.376, P&lt;0.001). Certain apparent errors, termed artificial stripe patterns, were not eliminated by QT. Applying QT to exclude low-quality pixels can minimize measurement error and improve differentiation of liver fibrosis grades. The presence of an artificial stripe pattern on the SWE map may indicate images requiring exclusion.

A novel AI-powered method for robust identification of operational phases in refrigerators

Refrigerators are essential appliances in our daily lives, while the accurate identification of their operational phase is crucial for various applications, such as energy management and maintenance. This paper introduces a novel method to predict the operational phase of refrigerators based on power consumption data, exploiting artificial intelligence (AI) and pattern recognition techniques. Specifically, the proposed method initially identifies the driving speed of the compressor (fixed or variable speed) utilizing an Adaptive Boosting, (AdaBoost) classifier. Following that, a Long Short-Term Memory (LSTM) classifier was designed for each type of compressor based on extracted statistical features. This classifier is used to categorize daily power consumption into the different operational phases. Moreover, the proposed AI-driven diagnostic tool facilitates operational-based prescriptive maintenance by addressing periodic and phase-specific maintenance actions while providing homeowners with informed suggestions on alternative refrigerator models that offer greater cost savings and reduced annual energy consumption. The proposed method was tested on real and simulated data for over 20 years, with the AdaBoost classifier achieving an accuracy close to 97% and an F1 score close to 97% and the LSTM nodes achieving an accuracy of approximately 95% in all cases. Finally, the method demonstrated robustness when applied to new datasets, showing comparable performance on unknown data, rendering it a powerful tool for refrigerator management and maintenance.

Efficient water-related failure detection in PEM fuel cells: Combining a PEMFCs fractional order impedance model with FFT-PWM techniques and artificial neural network classification

Water management and early detection of faults in proton exchange membrane fuel cells (PEMFCs) are among the most critical constraints that limit the optimal spread of this type of energy. Consequently, it is necessary to enhance the reliability and durability of PEMFCs by developing an approach to diagnose and identify water failure modes. This paper proposes an effective and simple method to detect, diagnose, and classify various water failure modes in PEMFCs using a hybrid diagnostic approach. This approach combines the PEMFC fractional order impedance model (FOIM) with fast Fourier transform pulse width modulation (FFT-PWM) techniques and artificial neural network pattern recognition (ANN-PR) classification. The results show an accurate match between the electrochemical impedance spectroscopy (EIS) experimental data, the Nyquist impedance spectra of FOIM, and the FFT-PWM algorithm as a proposed alternative technique to EIS measurements. Learning of ANN-PR was performed using the frequency spectrum amplitude (FSA) database of the voltage and current signals produced by the PEMFCs FOIM DC/DC boost converter, which was generated using the FFT-PWM algorithm. The ANN-PR achieved low values for error accuracy, with the Low Square Error and Learning Error reaching 6.676 × 10−19 and 1.888 × 10−16, respectively. The elements inside the confusion matrix and the rest of the matrices confirm that the proposed model's accuracy, precision, recall, and high F1 score reached 100%. Furthermore, all predictions made by the ANN-PR model were consistently accurate across all areas of failure detection. Overall, the proposed method helps in analyzing, diagnosing, and classifying fuel cell failure modes such as flooding and drying, which may simplify the health assessment of PEMFC.

A close-up view of the intra-ring variation of transverse shrinking and swelling in Chinese fir using digital image correlation without artificial speckle pattern

A close-up view of the intra-ring variation of transverse shrinking and swelling in Chinese fir using digital image correlation without artificial speckle pattern

Retracted: Intelligent Auxiliary Artificial Wood Plank Pattern Design Based on the Subject Search Algorithm of Multimedia Resources

Retracted: Intelligent Auxiliary Artificial Wood Plank Pattern Design Based on the Subject Search Algorithm of Multimedia Resources

An unbiased artificial referee in beauty contests based on pattern recognition and AI

Beauty contests have long been popular, but concerns about fairness and bias in judgment have emerged. To address this, integrating artificial intelligence (AI) and pattern recognition (PR) as an unbiased referee shows promise. This paper aims to assess the significance of different facial features, including eyes, nose, lips, chin, eyebrows, and jaws, as well as the role of angles and geometric facial measurements, such as distances between facial landmarks and ratios, in the context of beauty assessment. This study also employs two techniques, namely Principal Component Analysis (PCA) and stacked regression, to predict the attractiveness of faces. The experimental data set used for evaluation is the SCUT-FBP benchmark database. The obtained results, indicated by Mean Absolute Errors (MAE) and Pearson's Correlation Coefficient (PCC), demonstrate the high accuracy of our attractiveness prediction model. This research contributes to the advancement of automatic facial beauty analysis and its practical implications. Furthermore, our results surpass those published recently, further validating the effectiveness of our approach.

Automatic calibration system of thermo-hygrometers

Machine vision technology is an interdisciplinary subject involving plenty of fields such as artificial intelligence, neurobiology, psychophysics, computer science, image processing and pattern recognition, etc. In recent years, with rapid development of the technology, machine vision recognition is widely used in many fields of detection and control. For thermo-hygrometers calibration, the manual operation method is used traditionally. This has proven to be a cumbersome, time-consuming, and error-prone activity, as there are lots of models and quantities of thermo-hygrometers to be calibrated. Therefore, an automatic thermo-hygrometers calibration system was developed by using vision recognition technology in combination with automatic movement control as well as a purposely structured database management software. It can complete the calibration and the verification task accurately, timely and efficiently. It has drastically reduced the workload, improved accuracy, and realized the automatic calibration of the thermo-hygrometers.

Selective 3-dimensional patterning during phase separation of a continuously laminated layer

Control over the physical properties of materials is ubiquitously required in many fields. One means by which this can be achieved is controlling the internal structure of multi-component materials with an eye to enhancing mechanical properties. Here, we focus on self-organized pattern formation in phase separating materials, where microscopic patterns with a smooth, continuous connection may be realized. We propose a feasible method to control pattern formation using phase separation combined with continuous ``lamination'' of material, when material is continuously and homogeneously layered on top of a base. We find that a random droplet pattern, a lamellar pattern, and a cylindrical pattern are formed depending on the lamination rate $V$. We clarify the dynamics of pattern formation, focusing on the mechanism. This study may lead to the creation of new functional materials through artificial pattern control.

Abstract SY30-03: Composing each patient’s equation: Unraveling brain tumor complexity by integrating multi-regional image-localized biopsies

Abstract Glioblastoma is a uniquely challenging and aggressive cancer that is practically considered uniformly fatal. This aggressiveness is driven by heterogeneity between and within patients and the diffuse invasion of tumor cells deep into the normal appearing brain tissue surrounding the frank tumor abnormality. Mathematical neuro-oncology (MNO) is a burgeoning field that seeks to bring together individual patient data (like patient imaging, tissue biopsies etc) to tune mathematical models that accurately predict and quantify response to treatments for each patient. These mathematical models use both mechanistic “weather forecasting” methods and artificial intelligence pattern recognition methods. Ultimately, these models form the basis of modern "precision medicine" approaches to tailor therapy in a patient-specific manner. These models can be used to overcome the limited ability of imaging to accurately detect tumor cells, improve prognostic predictions, stratify patients, and assess treatment response in silico in the construction of effective clinical trials and treatment protocols, thus accelerating the pace of clinical research. This presentation will focus on the growing translation of MNO to clinical neuro-oncology highlighting burgeoning insights into sex differences in tumor incidence, outcomes, and response to therapy. Specifically, I will discuss 1) use of our 4,500+ patient cohorts of 100,000+ annotated serial MR imaging data to develop digital twins accurately predict response and outcomes in patients and 2) our unique collection of 1000+ image-localized biopsies across nearly 200 patients to detect sex-distinct patterns of mapping between regional imaging features and underlying regional tumor biology. We will demonstrate the value of these novel combined resources in predicting response to treatment for EGFR-targeted therapies in 3 clinical trials and differentiating response to novel dendritic cells vaccines and CAR T-cell therapies in 2 additional clinical trials. Taken together, these complimentary approaches provide a platform to incorporate inter- and intra- tumoral heterogeneity into accurate predictive models that advance precision oncology for glioblastoma patients. Citation Format: Kristin R. Swanson. Composing each patient’s equation: Unraveling brain tumor complexity by integrating multi-regional image-localized biopsies. [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2023; Part 1 (Regular and Invited Abstracts); 2023 Apr 14-19; Orlando, FL. Philadelphia (PA): AACR; Cancer Res 2023;83(7_Suppl):Abstract nr SY30-03.

Facial expression classification

At present, emotion classification has become a hot topic in artificial intelligence pattern recognition. The facial expression recognition (FER) is indispensable for computers to understand the emotional information conveyed by expressions. In the past, using traditional features to extract and classify facial expressions has not achieved satisfactory accuracy, so the classification of facial emotions is still a challenge. The model used in the paper is an existing one - MINI_XCEPTION, the dominant framework for CNNs that extracts features from images to identify and classify seven facial emotions. The model was trained on a dataset of people’s facial expressions (Kaggle). This model has a significant improvement over the previous model.

New technology using crystalline lens autofluorescence for presbyopia and cataract grading.

To investigate whether fundus autofluorescence (FAF) obtained using an ultra-wide field (UWF) fundus camera with an artificial opacity pattern can grade the degree of presbyopia and nuclear cataract. Sixty eyes of 30 patients were enrolled in this prospective diagnostic study. The nuclear cataract (nuclear color/opalescence (NC/NO)) was graded according to the Lens Opacity Classification System III. The monocular near point of accommodation (NPA) was measured in eyes with NC3/NO3 or less. The mean gray value difference between the central 8 artificial opacity lesions and peripheral 8 artificial opacity lesions in the retinal AF was measured. The correlation between the mean gray value difference, NPA, and nuclear cataract grade was analyzed. The mean nuclear cataract grade of 60 eyes was 3.2 ± 1.6 and mean NPA of 37 eyes was 45.3 ± 16.1 cm. The mean gray value differences increased with increasing nuclear cataract grade (eyes with NC/NO grade 1, 53.3 ± 11.4; 2, 78.3 ± 13.6; 3, 95.2 ± 12.2; 4, 101.6 ± 11.9; 5, 109.0 ± 22.9; and 6, 121.1 ± 12.0; p < 0.001). The mean gray value difference was positively correlated with both the monocular NPA (R2 = 0.637; β coefficient = 1.009; 95% CI, 0.748 to 1.271; p < 0.001) and nuclear cataract grade (R2 = 0.661; β coefficient = 12.437; 95% CI, 10.097 to 14.778; p < 0.001). The FAF camera with an artificial opacity pattern attached can be used to effectively diagnose the degree of presbyopia and nuclear cataract.

Artificial intelligence-supported pattern recognition

It is crucial to investigate pattern recognition in the quickly changing field of artificial intelligence. It is becoming more and more important to comprehend the nuances of AI-supported pattern recognition as we move through a time of unparalleled technological growth. This study undertakes a thorough investigation of the topic, exploring the fundamental elements that underpin AI-supported pattern recognition, looking into its various application areas, and casting a glance ahead to show upcoming developments. The ubiquitous influence of pattern recognition across multiple areas highlights the significance of AI in the current technological environment. The ability of AI systems to recognize and understand patterns in data is revolutionary in a variety of fields. The complexities of pattern recognition are becoming a focus for scholars, practitioners, and technologists alike as we approach a new era where AI is incorporated into our daily lives. In my research, I put forward three hypotheses that I am investigating during my research, and I am looking for the possible answers. H1: Artificial intelligence-supported pattern recognition will keep developing, and allowing machines to mimic and even exceed human abilities in seeing and processing complicated data. H2: Artificial intelligence will increasingly integrate with and improve a variety of industries as it develops. H3: The European Union has committed significant financial resources to support the development of AI in recognition of the technology's strategic importance. The main objective of this research is to get a deeper understanding of AI-supported pattern recognition by dissecting its complex components and illuminating its significant consequences for both the present and the future.

Current-Induced Helicity Switching of Frustrated Skyrmions on a Square-Grid Obstacle Pattern

Topological spin textures on artificial pinning landscape may show unique static and dynamic properties. Here, we computationally show that the helicity of frustrated skyrmions on an artificial square-grid obstacle pattern can be switched by a spin current pulse. The obstacle pattern is formed by defect lines with enhanced perpendicular magnetic anisotropy, which could protect the skyrmion from being annihilated at the sample edge. It is found that the skyrmion driven by a moderate current shows a circular motion guided by the boundary of the obstacle pattern, while it shows an almost straight motion toward the sample edge in the absence of the obstacle pattern. By applying a short pulse current to drive the skyrmion in a sample with the obstacle pattern, we find that the helicity of the skyrmion could be switched between Bloch-type configurations favored by the dipole-dipole interaction. Besides, we demonstrate the possibility of switching the helicity of an array of skyrmions on the square-grid obstacle pattern using the same method. Our results could be useful for the helicity control of topological spin textures, and may provide guidelines for building future helicity-based spintronic functions.

Pattern recognition describing spatio-temporal drivers of catchment classification for water quality

Classification using spatial data is foundational for hydrological modelling, particularly for ungauged areas. However, models developed from classified land use drivers deliver inconsistent water quality results for the same land uses and hinder decision-making guided by those models. This paper explores whether the temporal variation of water quality drivers, such as season and flow, influence inconsistency in the classification, and whether variability is captured in spatial datasets that include original vegetation to represent the variability of biotic responses in areas mapped with the same land use. An Artificial Neural Network Pattern Recognition (ANN-PR) method is used to match catchments by Dissolved Inorganic Nitrogen (DIN) patterns in water quality datasets partitioned into Wet vs Dry Seasons and Increasing vs Retreating flows. Explainable artificial intelligence approaches are then used to classify catchments via spatial feature datasets for each catchment. Catchments matched for sharing patterns in both spatial data and DIN datasets were corroborated and the benefit of partitioning the observed DIN dataset evaluated using Kruskal Wallis method. The highest corroboration rates for spatial data classification with DIN classification were achieved with seasonal partitioning of water quality datasets and significant independence (p < 0.001 to 0.026) from non-partitioned datasets was achieved. This study demonstrated that DIN patterns fall into three categories suited to classification under differing temporal scales with corresponding vegetation types as the indicators. Categories 1 and 3 included dominance of woodlands in their datasets and catchments suited to classify together change depending on temporal scale of the data. Category 2 catchments were dominated by vineforest and classified catchments did not change under different temporal scales. This demonstrates that including original vegetation as a proxy for differences in DIN patterns will help guide future classification where only spatially mapped data is available for ungauged catchments and will better inform data needs for water modelling.

Artificial Neural Network-Based Abnormal Gait Pattern Classification Using Smart Shoes with a Gyro Sensor

Recently, as a wearable-sensor-based approach, a smart insole device has been used to analyze gait patterns. By adding a small low-power sensor and an IoT device to the smart insole, it is possible to monitor human activity, gait pattern, and plantar pressure in real time and evaluate exercise function in an uncontrolled environment. The sensor-embedded smart soles prevent any feeling of heterogeneity, and WiFi technology allows acquisition of data even when the user is not in a laboratory environment. In this study, we designed a sensor data-collection module that uses a miniaturized low-power accelerometer and gyro sensor, and then embedded it in a shoe to collect gait data. The gait data are sent to the gait-pattern classification module via a Wi-Fi network, and the ANN model classifies the gait into gait patterns such as in-toeing gait, normal gait, or out-toeing gait. Finally, the feasibility of our model was confirmed through several experiments.

Heat transmission and air flow friction in a solar air heater with a ribbed absorber plate: A computational study

The influence of geometrical parameters of V-symmetry ribs on heat flow and fluid flow characteristics of solar air heater (SAH) rectangular duct with ribbed absorber is investigated theoretically. Fabrication of ribs in repeated artificial protrusions pattern on the absorber surface appears as a simple approach for increasing the solar collectors radiation harnessing capacity. The various characteristics of artificial roughness protrusions include relative roughness height (e/Dh), relative roughness pitch (p/e), and angle of attack of flow (α), and the span of these parameters is determined based on experimental considerations of the device and working circumstances. To measure the improvement in the coefficient of heat transfer and friction factor, the outcomes were correlated to those of a smooth conduit under identical flow characteristics. The greatest increase in Stanton number and friction factor is 1.13 and 1.19 folds that of the smooth SAH duct, correspondingly.

Poly(thioctic acid): From Bottom-Up Self-Assembly to 3D-Fused Deposition Modeling Printing.

Inspired by the bottom-up assembly in nature, an artificial self-assembly pattern is introduced into 3D-fused deposition modeling (FDM) printing to achieve additive manufacturing on the macroscopic scale. Thermally activated polymerization of thioctic acid (TA) enabled the bulk construction of poly(TA), and yielded unique time-dependent self-assembly. Freshly prepared poly(TA) can spontaneously and continuously transfer into higher-molecular-weight species and low-molecular-weight TA monomers. Poly(TA) and the newly formed TA further assembled into self-reinforcing materials via microscopic-phase separation. Bottom-up self-assembly patterns on different scales are fully realized by 3D FDM printing of poly(TA): thermally induced polymerization of TA (microscopic-scale assembly) to poly(TA) and 3D printing (macroscopic-scale assembly) of poly(TA) are simultaneously achieved in the 3D-printing process; after 3D printing, the poly(TA) modes show mechanically enhanced features over time, arising from the microscopic self-assembly of poly(TA) and TA. This study clearly demonstrates that micro- and macroscopic bottom-up self-assembly can be applied in 3D additive manufacturing.