Class Of Patterns Research Articles

Effect of body mass index on soft tissues in adolescents with skeletal class I and normal facial height.

The evaluation of soft tissues in patients undergoing orthodontic treatment plays a critical role in diagnosis and treatment planning. This study aims to evaluate the effect of body mass index (BMI) on facial soft tissues in skeletal Class I patients with normal vertical growth. The study included 72 patients with a normal vertical growth pattern (SN-GoGn 26-38°) and skeletal Class I (ANB 2‒4°) malocclusion. According to their BMI (kg/m2) values, the patients were divided into three groups of 24 individuals each: underweight (>5th percentile) (13 females, 11 males; mean age, 11.58 ± 1.95 years), normal weight (5‒85th percentile) (12 females, 12 males; mean age, 11.54 ± 1.95 years), overweight (85‒95th percentile) (12 females, 12 males; mean age, 11.62 ± 2.01 years). Soft tissue thickness and height measurements were made on lateral cephalometric radiographs. In all soft tissue thickness measurements, except for the nasion, the overweight weight group had higher values. In comparing the underweight and normal weight groups, statistically significant differences were found in the thickness measurements at the nasion and gnathion (p < 0.05). The differences in thickness measurements at the glabella, labiale superius, stomion, labiale inferius, pogonion, gnathion, and menton are statistically significant between the underweight and overweight groups (p < 0.005). Comparing the normal and overweight groups revealed statistically significant differences the thickness measurements at the glabella, labiale superius, stomion, pogonion and menton (p < 0.05).

Pattern-moving-based dynamic description for a class of nonlinear systems using the generalized probability density evolution

For a class of complex nonlinear systems governed by statistical laws, a new pattern-moving-based description method using the generalized probability density evolution was proposed. Due to the fact that the states and outputs of such systems typically exhibit a probability distribution rather than deterministic variables, and the outputs obtained by the system under similar operating conditions typically exhibit similar performance, a pattern class variable was constructed to describe such systems and effectively estimate their outputs or states. The mapping relationship between states and pattern class variables was established through the probability density evolution of the system. First, the dynamic description based on pattern moving is constructed by classification metric mapping. Then, the prior probability of the system state was predicted by solving the generalized density evolution equation. Next, the posterior probability was updated recursively according to Bayesian formula. Finally, the maximum a posteriori probability criterion is used to estimate the system state. The feasibility and effectiveness of the proposed algorithm were verified by numerical examples.

HiREX: High-Throughput Reactivity Exploration for Extended Databases of Transition-Metal Catalysts.

A method is introduced for the automated analysis of reactivity exploration for extended in silico databases of transition-metal catalysts. The proposed workflow is designed to tackle two key challenges for bias-free mechanistic explorations on large databases of catalysts: (1) automated exploration of the chemical space around each catalyst with unique structural and chemical features and (2) automated analysis of the resulting large chemical data sets. To address these challenges, we have extended the application of our previously developed ReNeGate method for bias-free reactivity exploration and implemented an automated analysis procedure to identify the classes of reactivity patterns within specific catalyst groups. Our procedure applied to an extended series of representative Mn(I) pincer complexes revealed correlations between structural and reactive features, pointing to new channels for catalyst transformation under the reaction conditions. Such an automated high-throughput virtual screening of systematically generated hypothetical catalyst data sets opens new opportunities for the design of high-performance catalysts as well as an accelerated method for expert bias-free high-throughput in silico reactivity exploration.

A morphological study of fivefold Islamic geometric patterns using formal grammar for computer-aided design applications

This paper presents a morphological study of Islamic geometric patterns (IGP) and their role in application of formal grammar in computational modeling of IGPs. Through a comprehensive literature review and data collection, we analyze the morphological properties of these patterns using techniques such as geometric transformations, pattern classification, and symmetry analysis. Based on our findings, we explore how these properties can be used in constructing a formal grammar through string rewriting system for a CAD application. Building on a study on the potential of a string rewriting system for modeling IGPs, the current research suggests an update to the previous system and introduces a new morphological structure for IGPs. The new method has an expanded sample set and is tested on a class of 5-fold star patterns with 12 members and demonstrates successful development. The results are implemented in a Grasshopper add-on, providing a flexible platform to generate the patterns through strings and to control their parameters. This tool opens up new possibilities to bridge traditional patterns with contemporary technologies and make them more accessible. Furthermore, it contributes to the preservation of IGPs as a significant cultural and architectural heritage, while also advancing the evolution of these patterns to a new and contemporary generation.

Lip Prints as an Early Indicator of Different Malocclusions

ntroduction: The goal of the current investigation was to see if there was any correlation between skeletal malocclusions and lip print patterns. Settings and Design: Hospital based, prospective, observational, cross-sectional study. Meterials and Methods: The study was conducted on 120 subjects, divided into 3 groups Skeletal Class I, Class II, and Class III based on ANB angle, Beta angle, and Wits. For the assessment of lip print patterns, they were classifi ed according to the Tsuchihashi classification system. Statistical analysis: The chi-square test was used to study diff erences in the groups. Results: It was noted that the most prevalent lip pattern was Type I while; the least was the Type V pattern. A Type III lip pattern was absent. There was a signifi cant correlation between Type I lip pattern and Skeletal Class III malocclusion. Also, there were signifi cant gender diff erences in lip print patterns in skeletal class I malocclusion with no diff erences in skeletal class II and class III malocclusion. Conclusion: Lip prints can be a useful aid in predicting the type of skeletal malocclusion as they develop early in life, therefore, can be successfully used for preventative and interceptive orthodontic procedures. Hence, lip prints can be used as early detectors of skeletal malocclusions. Key Messages: Since the craniofacial skeleton and lips print both develop at the same embryonic stage, developmental variables that result in malocclusions may also be refl ected in the lip print patterns.

AdaDeepStream: streaming adaptation to concept evolution in deep neural networks

Typically, Deep Neural Networks (DNNs) are not responsive to changing data. Novel classes will be incorrectly labelled as a class on which the network was previously trained to recognise. Ideally, a DNN would be able to detect changing data and adapt rapidly with minimal true-labelled samples and without catastrophically forgetting previous classes. In the Online Class Incremental (OCI) field, research focuses on remembering all previously known classes. However, real-world systems are dynamic, and it is not essential to recall all classes forever. The Concept Evolution field studies the emergence of novel classes within a data stream. This paper aims to bring together these fields by analysing OCI Convolutional Neural Network (CNN) adaptation systems in a concept evolution setting by applying novel classes in patterns. Our system, termed AdaDeepStream, offers a dynamic concept evolution detection and CNN adaptation system using minimal true-labelled samples. We apply activations from within the CNN to fast streaming machine learning techniques. We compare two activation reduction techniques. We conduct a comprehensive experimental study and compare our novel adaptation method with four other state-of-the-art CNN adaptation methods. Our entire system is also compared to two other novel class detection and CNN adaptation methods. The results of the experiments are analysed based on accuracy, speed of inference and speed of adaptation. On accuracy, AdaDeepStream outperforms the next best adaptation method by 27% and the next best combined novel class detection/CNN adaptation method by 24%. On speed, AdaDeepStream is among the fastest to process instances and adapt.

Are Physical and Depressive Symptoms Different Between Women and Men With Heart Failure?: An Exploration Using Two Analytic Techniques.

Adults with heart failure (HF) experience a constellation of symptoms; however, understanding of gender differences in HF symptoms remain elusive. The aim of this study was to determine whether there are gender differences in physical and depressive symptoms and symptom patterns in HF using 2 different analytic techniques. We performed a secondary analysis of combined data from 6 studies of adults with HF. Physical symptoms were measured with the HF Somatic Perception Scale, and depressive symptoms were measured with the Patient Health Questionnaire-9. First, we performed propensity matching with the nearest neighbor to examine the average treatment effect for HF Somatic Perception Scale and Patient Health Questionnaire-9 in the matched sample of women and men. Next, we used the entire data set in a latent class mixture model to determine patterns of symptoms. Finally, we calculated predictors of class membership with multinomial logistic regression. The sample (n = 524, 86.5% systolic HF) was 37% women with a mean age of 58.3 ± 13.9 years and mean number of years with HF of 6.9 ± 6.9. Three hundred sixty-six participants were matched on propensity scores; there were no significant gender differences in symptom scores between matched women (n = 183) and men (n = 183). Among all 524 participants, 4 distinct latent classes of symptom patterns indicate that many patients with HF are fatigued, some have more depressive symptoms, and others have significantly more edema or cough. Gender did not predict membership to any symptom pattern. There were significant gender differences in sociodemographics, health behaviors, and clinical characteristics, but not HF symptoms or symptom patterns, using either analytic technique.

Effects of multimorbidity patterns and socioeconomic status on catastrophic health expenditure of widowed older adults in China.

The high multimorbidity and lower socioeconomic status (SES) of older adults, can lead to catastrophic health expenditures (CHEs) for older adults' households. However, whether widowed older adults will bear such a financial burden has yet to be explored. The aim of this study was to investigate the influence of multimorbidity patterns and SES on CHE in Chinese widowed older adults. Data was obtained from the 2018 China Health and Retirement Longitudinal Study (CHARLS). This is a cross-sectional study. A total of 1,721 widowed participants aged 60 years and older were enrolled in the study. Latent class analysis was performed based on 14 self-reported chronic diseases to identify multimorbidity patterns. The logistic model and Tobit model were used to analyze the influence of multimorbidity patterns and SES on the incidence and intensity of CHE, respectively. About 36.72% of widowed older adults generated CHE. The incidence and intensity of CHE were significantly higher in the cardiovascular class and multisystem class than in the minimal disease class in multimorbidity patterns (cardiovascular class, multisystem class, and minimal disease class). Among SES-related indicators (education, occupation and household per capita income), respondents with a middle school and above education level were more likely to generate CHE compared to those who were illiterate. Respondents who were in the unemployed group were more likely to generate CHE compared to agricultural workers. In addition, respondents aged 70-79 years old, geographically located in the east, having other medical insurance, or having fewer family members are more likely to generate CHE and have higher CHE intensity. Widowed older adults are at high risk for CHE, especially those in the cardiovascular and multisystem disease classes, and those with low SES. Several mainstream health insurances do not provide significant relief. In addition, attention should be paid to the high-risk characteristics associated with CHE. It is necessary to carry out the popularization of chronic disease knowledge, improve the medical insurance system and medical service level, and provide more policy preferences and social support to widowed older adults.

Spectral features of non-nutritive suck dynamics in extremely preterm infants.

Non-nutritive suck (NNS) is used to promote ororhythmic patterning and assess oral feeding readiness in preterm infants in the neonatal intensive care unit (NICU). While time domain measures of NNS are available in real time at cribside, our understanding of suck pattern generation in the frequency domain is limited. The aim of this study is to model the development of NNS in the frequency domain using Fourier and machine learning (ML) techniques in extremely preterm infants (EPIs). A total of 117 EPIs were randomized to a pulsed or sham orocutaneous intervention during tube feedings 3 times/day for 4 weeks, beginning at 30 weeks post-menstrual age (PMA). Infants were assessed 3 times/week for NNS dynamics until they attained 100% oral feeding or NICU discharge. Digitized NNS signals were processed in the frequency domain using two transforms, including the Welch power spectral density (PSD) method, and the Yule-Walker PSD method. Data analysis proceeded in two stages. Stage 1: ML longitudinal cluster analysis was conducted to identify groups (classes) of infants, each showing a unique pattern of change in Welch and Yule-Walker calculations during the interventions. Stage 2: linear mixed modeling (LMM) was performed for the Welch and Yule-Walker dependent variables to examine the effects of gestationally-aged (GA), PMA, sex (male, female), patient type [respiratory distress syndrome (RDS), bronchopulmonary dysplasia (BPD)], treatment (NTrainer, Sham), intervention phase [1, 2, 3], cluster class, and phase-by-class interaction. ML of Welch PSD method and Yule-Walker PSD method measures revealed three membership classes of NNS growth patterns. The dependent measures peak_Hz, PSD amplitude, and area under the curve (AUC) are highly dependent on PMA, but show little relation to respiratory status (RDS, BPD) or somatosensory intervention. Thus, neural regulation of NNS in the frequency domain is significantly different for each identified cluster (classes A, B, C) during this developmental period. Efforts to increase our knowledge of the evolution of the suck central pattern generator (sCPG) in preterm infants, including NNS rhythmogenesis will help us better understand the observed phenotypes of NNS production in both the frequency and time domains. Knowledge of those features of the NNS which are relatively invariant vs. other features which are modifiable by experience will likewise inform more effective treatment strategies in this fragile population.

Learning phase transitions from regression uncertainty: a new regression-based machine learning approach for automated detection of phases of matter

Abstract For performing regression tasks involved in various physics problems, enhancing the precision or equivalently reducing the uncertainty of regression results is undoubtedly one of the central goals. Here, somewhat surprisingly, the unfavorable regression uncertainty in performing the regression tasks of inverse statistical problems is found to contain hidden information concerning the phase transitions of the system under consideration. By utilizing this hidden information, a new unsupervised machine learning approach was developed in this work for automated detection of phases of matter, dubbed learning from regression uncertainty. This is achieved by revealing an intrinsic connection between regression uncertainty and response properties of the system, thus making the outputs of this machine learning approach directly interpretable via conventional notions of physics. It is demonstrated by identifying the critical points of the ferromagnetic Ising model and the three-state clock model, and revealing the existence of the intermediate phase in the six-state and seven-state clock models. Comparing to the widely-used classification-based approaches developed so far, although successful, their recognized classes of patterns are essentially abstract, which hinders their straightforward relation to conventional notions of physics. These challenges persist even when one employs the state-of-the-art deep neural networks (NNs) that excel at classification tasks. In contrast, with the core working horse being an NN performing regression tasks, our new approach is not only practically more efficient, but also paves the way towards intriguing possibilities for unveiling new physics via machine learning in a physically interpretable manner.

A refined method for investigating the morphological and optical properties of a biodegradable monocryl suture

An interferometric computed tomography (ICT) technique with a refined method is proposed and analysed for investigating the morphology of the Monocryl surgical sutures during the degradation process. This method includes four integrated stages. In the first stage, the two-beam Pluta polarizing interference microscope is equipped with the rotational device for repeatedly recording the 2D interference patterns of the degraded sample at various angular rotations. The second stage in which an artificial intelligence model is designed to detect and remove the noise classes in the interference patterns. In the third stage, the computational Phase-Shifting interferometric approach (CPSI) is employed for demodulating the phase maps of the tested sample. Finally, autocorrelation and the filtered back projection (FBP) algorithms are utilized to explore the 3D phase morphology of the tested sample. The presented method is useful for determining the refractive indices and the birefringence during the whole degradation duration. Collectively, the results of the proposed method reveal that ICT technology has the potential to investigate the degradation performances of this kind of biodegradable polymer effectively.

Five classes of pattern avoiding inversion sequences under one roof: generating trees

An inversion sequence of length n is a word which satisfies for each the inequalities . In this paper, we present enumerations of four classes of inversion sequences that avoid a pattern of length 4. More precisely, we describe each class by a generating tree with 2 labels, and then we obtain an explicit formula for the generating function for the number of inversion sequences of length n that avoid either 0132, , , 0123, or 0321.

Carbohydrate Intakes below Recommendations with a High Intake of Fat Are associated with Higher Prevalence of Metabolic Syndrome.

More than one-third of adults in the United States have metabolic syndrome, and dietary carbohydrate intake may modify the likelihood of developing this condition. Currently, there is a lack of consistent evidence demonstrating the relationship between carbohydrate intake that falls below recommendations and metabolic syndrome. Not accounting for the differences in fatty acid classes of these dietary patterns may be a reason for inconsistent findings. This study evaluated the association between a carbohydrate intake below recommendations and metabolic syndrome stratified by fat quantity and fatty acid classes in a nationally representative sample of US adults. This cross-sectional study acquired data on food and nutrient intake and markers of metabolic syndrome from respondents in the National Health and Nutrition Examination Survey 1999-2018. This study included 19,078 respondents who were aged 20 years or older, had reliable and complete data on food and nutrient intake and markers of metabolic syndrome, and were not pregnant or breastfeeding. The main outcome was prevalence of metabolic syndrome. Usual dietary intake was estimated using the National Cancer Institute's usual intake methodology. Multivariable logistic regression models assessed the relative odds of prevalent metabolic syndrome between those who had a carbohydrate intake below recommendations and those who met carbohydrate recommendations. Those who had a carbohydrate intake below recommendations had 1.067 (95% CI 1.063 to 1.071) times greater odds of having metabolic syndrome compared with those who met carbohydrate recommendations (P < 0.001). High intake of fat of any class was associated with higher odds of metabolic syndrome (total fat: 1.271, 95% CI 1.256 to 1.286; saturated fatty acid: 1.072, 95% CI 1.060 to 1.085; monounsaturated fatty acid: 1.317, 95% CI 1.300 to 1.333; polyunsaturated fatty acid: 1.056, 95% CI 1.047 to 1.066; P < 0.001 for all comparisons) in those who had a carbohydrate intake below recommendations. The odds of prevalent metabolic syndrome were higher among individuals who had a carbohydrate intake below recommendations compared with individuals who met carbohydrate recommendations.

The dynamics of pattern matching in camouflaging cuttlefish

Many cephalopods escape detection using camouflage1. This behaviour relies on a visual assessment of the surroundings, on an interpretation of visual-texture statistics2–4 and on matching these statistics using millions of skin chromatophores that are controlled by motoneurons located in the brain5–7. Analysis of cuttlefish images proposed that camouflage patterns are low dimensional and categorizable into three pattern classes, built from a small repertoire of components8–11. Behavioural experiments also indicated that, although camouflage requires vision, its execution does not require feedback5,12,13, suggesting that motion within skin-pattern space is stereotyped and lacks the possibility of correction. Here, using quantitative methods14, we studied camouflage in the cuttlefish Sepia officinalis as behavioural motion towards background matching in skin-pattern space. An analysis of hundreds of thousands of images over natural and artificial backgrounds revealed that the space of skin patterns is high-dimensional and that pattern matching is not stereotyped—each search meanders through skin-pattern space, decelerating and accelerating repeatedly before stabilizing. Chromatophores could be grouped into pattern components on the basis of their covariation during camouflaging. These components varied in shapes and sizes, and overlay one another. However, their identities varied even across transitions between identical skin-pattern pairs, indicating flexibility of implementation and absence of stereotypy. Components could also be differentiated by their sensitivity to spatial frequency. Finally, we compared camouflage to blanching, a skin-lightening reaction to threatening stimuli. Pattern motion during blanching was direct and fast, consistent with open-loop motion in low-dimensional pattern space, in contrast to that observed during camouflage.

Using Machine-Learning to Predict Sleep-Disordered Breathing Diagnosis From Medical Comorbidities and Craniofacial Features.

Objectives This paper attempts to use machine-learning (ML) algorithms to predict the presence of sleep-disordered breathing (SDB) in a patient based on their body habitus, craniofacial anatomy, and social history. Materials and methods Data from a group of 69 adult patients who attended a dental clinic for oral surgeries and dental procedures in the last 10 years was used to train machine-learning models to predict whether a subject is likely to have SDB based on input information such as age, gender, smoking history, body mass index (BMI), oropharyngeal airway (Mallampati assessment), forward head posture (FHP), facial skeletal pattern, and sleep quality. Logistic Regression (LR), K-nearest Neighbours (kNN), Support Vector Machine (SVM) and Naïve Bayes (NB) were selected as these are the most frequently used supervised machine-learning models for classification of outcomes. The data was split into two sets for machine training (80% of total records) and the remaining was used for testing (validation). Results Initial analysis of collected data showed overweight BMI (at 25 or above), periorbital hyperchromia (dark circle eyes), nasal deviation, micrognathia, convex facial skeletal pattern (class 2) and Mallampati class 2 or above have positive correlations with SDB. Logistic Regression was found to be the best performer amongst the four models used with an accuracy of 86%, F1 score of 88% and area under the ROC curve (AUC) of 93%. LR also had 100% specificity and 77.8% sensitivity. Support Vector Machine was the second-best performer with an accuracy of 79%, F1 score of 82% and AUC of 93%. k-Nearest Neighbours and Naïve Bayes performed reasonably well with F1 scores of 71% and 67%, respectively. Conclusions This study demonstrated the feasibility of using simple machine-learning models as a credible predictor of sleep-disordered breathing in patients with structural risk factors for sleep apnoea such as craniofacial anomalies, neck posture and soft tissue airway obstruction. By utilising higher-level machine-learning algorithms, it is possible to incorporate a broader range of risk factors, including non-structural features like respiratory diseases, asthma, medication use, and more, into the prediction model.

Drug Utilization Pattern and Potentially Inappropriate Medications among Elderly Inpatients in a Tertiary Care Hospital in Western Nepal

Introduction: Drug utilization research deals with the quality of care focusing on potentially inappropriate medication (PIM), The objectives of the study were to assess the drug utilization pattern (class of drugs used, average number of drugs per prescription per encounter, number of drug prescribed in generic name and antibiotics in prescription) and potentially inappropriate medications and their categories among elderly inpatients.&#x0D; Methods: It was a prospective observational study carried out in the medical department of Western Regional Hospital, one of the tertiary level public referral hospital in Pokhara, Nepal. One hundred and two patients of both sexes, age above 65 years and who were hospitalized in medical department were selected. The patients were followed until their discharge to obtain complete information about the drugs being used. Patient data collection form and Updated 2012 Beers Criteria were used to assess drug utilization patterns and determine PIM respectively.&#x0D; Results: Most of the patients were in the age group of 65-70 (37.25%) followed by 71-75 (27.45%) and 76-80 (18.62%). Out of 102 patients, 53 (51.97%) were male and 49 (48.03 %) were female. Antimicrobials were the most prescribed medicines (16.73%). Average number of drugs per prescription per encounters, number of drug prescribed in generic name and number of antibiotics in prescription were 7.26, 9.6% and 21% respectively. About 57% of medicines were prescribed from the national essential medicine list. Among them, 20 (3.91%) of all drugs had at least one PIM. There were 27 drugs in Beers criteria A, one drug in Beers criteria B, and no drug in Beers criteria C.&#x0D; Conclusion: Antibiotic prescription was found within the optimal values whereas values of other prescribing indicators were out of the optimal values in comparing earlier studies. PIM was observed in prescriptions that suggest irrational practice and the need for interventions.

Learning smooth dendrite morphological neurons for pattern classification using linkage trees and evolutionary-based hyperparameter tuning

The current learning approach for smooth dendrite morphological neurons (DMNs) determines dendrite parameters using k-means clustering, which is non-reproducible due to its stochastic nature, risking falling into local minima. To overcome this issue, we introduce a DMN learning approach based on a deterministic hierarchical clustering method, which builds a linkage tree for each class of patterns. In addition, a micro genetic algorithm automatically tunes the cut-off points in the linkage trees hierarchy to create suitable clusters of dendrites. The classification experiments consider 40 real-world datasets. The proposed approach outperforms three DMN models in classification performance and is quite competitive with a hybrid morphological-linear perceptron, multilayer perceptron, random forest, and support vector machine. Therefore, the proposed method is a suitable alternative for pattern classification applications.

An algorithmic approach based on generating trees for enumerating pattern-avoiding inversion sequences

We introduce an algorithmic approach based on a generating tree method for enumerating the inversion sequences with various pattern-avoidance restrictions. For a given set of patterns, we propose an algorithm that outputs either an accurate description of the succession rules of the corresponding generating tree or an ansatz. By using this approach, we determine the generating trees for the pattern classes In(000,021), In(100,021), In(110,021), In(102,021), In(100,012), In(011,201), In(011,210) and In(120,210). Then we use the kernel method, obtain generating functions of each class, and find enumerating formulas. Lin and Yan studied the classification of the Wilf-equivalences for inversion sequences avoiding pairs of length-three patterns and showed that there are 48 Wilf classes among 78 pairs. In this paper, we solve six open cases for such pattern classes. Moreover, we extend the algorithm to restricted growth sequences and apply it to several classes. In particular, we present explicit formulas for the generating functions of the restricted growth sequences that avoid either {12313,12323}, {12313,12323,12333}, or {123⋯ℓ1}.

A two-stage deep graph clustering method for identifying the evolutionary patterns of the time series of animation view counts

Time-series clustering of view counts with changes in online time can identify animated series with similar evolutionary count patterns over time, which may help companies reduce their investment risk. For time-series data of animation view counts, most existing time-series clustering methods ignore both the local relationships within data and global relationships between data, making it challenging to identify animated series with similar evolutionary patterns. Therefore, we propose a two-stage deep graph clustering method that involves graph data construction and deep graph clustering. Specifically, graph data construction converts time-series data into graph data, while deep graph clustering uses a temporal convolutional network and graph convolutional network to learn features from the time-series data and graph data, respectively. The entire model is then trained end-to-end to complete the clustering task, utilizing a dual self-supervised module. This study utilizes two datasets to evaluate the clustering performance of our proposed model in comparison to baseline methods. The datasets consist of view count data from 185 animated series on Tencent Video from 2018 to 2022, as well as a public time-series BME dataset. The experimental results demonstrate that our model outperforms the baseline methods on both datasets. Additionally, through visualizing the identified three classes of evolutionary patterns, we propose new product development strategies for animation enterprises.

Longitudinal Assessment of Multimorbidity Medication Patterns among Smokers in the COPDGene Cohort.

Background and objectives: Chronic obstructive pulmonary disease (COPD) is usually comorbid with other chronic diseases. We aimed to assess the multimorbidity medication patterns and explore if the patterns are similar for phase 1 (P1) and 5-year follow-up phase 2 (P2) in the COPDGene cohort. Materials and Methods: A total of 5564 out of 10,198 smokers from the COPDGene cohort who completed 2 visits, P1 and P2 visits, with complete medication use history were included in the study. We conducted latent class analysis (LCA) among the 27 categories of chronic disease medications, excluding COPD treatments and cancer medications at P1 and P2 separately. The best number of LCA classes was determined through both statistical fit and interpretation of the patterns. Results: We found four classes of medication patterns at both phases. LCA showed that both phases shared similar characteristics in their medication patterns: LC0: low medication; LC1: hypertension (HTN) or cardiovascular disease (CVD)+high cholesterol (Hychol) medication predominant; LC2: HTN/CVD+type 2 diabetes (T2D) +Hychol medication predominant; LC3: Hychol medication predominant. Conclusions: We found similar multimorbidity medication patterns among smokers at P1 and P2 in the COPDGene cohort, which provides an understanding of how multimorbidity medication clustered and how different chronic diseases combine in smokers.