Clustering Accuracy Research Articles

Hybrid raven roosting intelligence framework for enhancing efficiency in data clustering

The field of data exploration relies heavily on clustering techniques to organize vast datasets into meaningful subgroups, offering valuable insights across various domains. Traditional clustering algorithms face limitations in terms of performance, often getting stuck in local minima and struggling with complex datasets of varying shapes and densities. They also require prior knowledge of the number of clusters, which can be a drawback in real-world scenarios. In response to these challenges, we propose the "hybrid raven roosting intelligence framework" (HRIF) algorithm. HRIF draws inspiration from the dynamic behaviors of roosting ravens and computational intelligence. What distinguishes HRIF is its effective capacity to adeptly navigate the clustering landscape, evading local optima and converging toward optimal solutions. An essential enhancement in HRIF is the incorporation of the Gaussian mutation operator, which adds stochasticity to improve exploration and mitigate the risk of local minima. This research presents the development and evaluation of HRIF, showcasing its unique fusion of nature-inspired optimization techniques and computational intelligence. Extensive experiments with diverse benchmark datasets demonstrate HRIF's competitive performance, particularly its capability to handle complex data and avoid local minima, resulting in accurate clustering outcomes. HRIF's adaptability to challenging datasets and its potential to enhance clustering efficiency and solution quality position it as a promising solution in the world of data exploration.

Multi-view clustering via double spaces structure learning and adaptive multiple projection regression learning

Multi-view clustering aims to group objects with high similarity into one group according to the heterogeneous features of different views. The graph-based clustering methods have obtained excellent results. However, there remain a few common drawbacks. For example, some methods do not consider graphs' high-order structure information. Thus, fuller data information cannot be obtained. In addition, some methods remove noise, outliers, and redundant information in the graph learning phase, resulting in the loss of graph information. Furthermore, using predefined graphs cannot exploit complementary information between views. A triple strategy-based multi-view clustering method is presented to solve the above issues. First, Laplacian graphs are used for fusion learning, and the underlying first-order and second-order structure information among views are explored simultaneously. Then, a label fusion scheme is designed to eliminate noise, outliers, and redundant information and to mine the intrinsic characteristics of data labels. Besides, the consistent label matrix in adaptive regression learning is used to explore complementary information between views in a mutually guided learning way. Finally, the objective function is solved by using an efficient iterative method. Six types of experiments are conducted on eleven real-world multi-view datasets, and the conclusions that can be drawn are: (1) the proposed algorithm achieves the best results in terms of clustering accuracy on ten datasets with an average accuracy improvement of 5.11% compared to other algorithms. Specifically, the accuracy improved by 9.05% on dataset HW and 10.95% on dataset Reuters compared to the second results; (2) The ablation experiments confirm that the different learning strategies included in the proposed algorithm allow it to achieve better clustering performance.

YOLOv8n-CSE: A Model for Detecting Litchi in Nighttime Environments

The accurate detection of litchi fruit cluster is the key technology of litchi picking robot. In the natural environment during the day, due to the unstable light intensity, uncertain light angle, background clutter and other factors, the identification and positioning accuracy of litchi fruit cluster is greatly affected. Therefore, we proposed a method to detect litchi fruit cluster in the night environment. The use of artificial light source and fixed angle can effectively improve the identification and positioning accuracy of litchi fruit cluster. In view of the weak light intensity and reduced image features in the nighttime environment, we proposed the YOLOv8n-CSE model. The model improves the recognition of litchi clusters in night environment. Specifically, we use YOLOv8n as the initial model, and introduce the CPA-Enhancer module with chain thinking prompt mechanism in the neck part of the model, so that the network can alleviate problems such as image feature degradation in the night environment. In addition, the VoVGSCSP design pattern in Slimneck was adopted for the neck part, which made the model more lightweight. The multi-scale linear attention mechanism and the EfficientViT module, which can be deeply divided, further improved the detection accuracy and detection rate of YOLOv8n-CSE. The experimental results show that the proposed YOLOv8n-CSE model can not only recognize litchi clusters in the night scene, but also has a significant improvement over previous models. In mAP@0.5 and F1, YOLOv8n-CSE achieved 98.86% and 95.54% respectively. Compared with the original YOLOv8n, RT-DETR-l and YOLOv10n, mAP@0.5 is increased by 4.03%, 3.46% and 3.96%, respectively. When the number of parameters is only 4.93 m, F1 scores are increased by 5.47%, 2.96% and 6.24%, respectively. YOLOv8n-CSE achieves an inference time of 36.5ms for the desired detection results. To sum up, the model can satisfy the criteria of the litchi cluster detection system for extremely accurate nighttime environment identification.

Perceptions Matter! Active Physical Recreation Participation of Children with High and Low Actual and Perceived Physical Competence.

Emerging evidence suggests that the accuracy of a child's perceived physical competence (PPC) impacts participation in physical activity. We examined differences in active physical recreation (APR) participation based on clusters of high and low motor competence and perceptions from grades 3-5. Participants were a longitudinal sample (n = 155; 85 girls) of grade three, four, and five children. Fundamental motor skills (FMSs) were assessed using the TGMD-2, perceptions were assessed using the Self-Perception Profile for Children, and APR was measured using the Children's Assessment of Participation and Enjoyment. K-means cluster analysis was used to create four clusters per grade based on participants' FMSs and PPC z-scores. Differences in FMSs, PPC, and APR with cluster group as a factor were examined using a series of factorial ANOVAs. In each grade, participants in the high-high cluster participated in significantly more APR than those in the low-low cluster (p = 0.002 in grades three and four; p < 0.001 in grade five). Among the less accurate clusters (e.g., low FMSs with high PPC) was a trend toward positive FMSs growth among the children with higher perceptions. Results show that combinations of FMSs and PPC influence patterns of engagement or disengagement in active physical recreation persistently across middle childhood.

Improving unsupervised pedestrian re‐identification with enhanced feature representation and robust clustering

AbstractPedestrian re‐identification (re‐ID) is an important research direction in computer vision, with extensive applications in pattern recognition and monitoring systems. Due to uneven data distribution, and the need to solve clustering standards and similarity evaluation problems, the performance of unsupervised methods is limited. To address these issues, an improved unsupervised re‐ID method, called Enhanced Feature Representation and Robust Clustering (EFRRC), which combines EFRRC is proposed. First, a relation network that considers the relations between each part of the pedestrian's body and other parts is introduced, thereby obtaining more discriminative feature representations. The network makes the feature at the single‐part level also contain partial information of other body parts, making it more discriminative. A global contrastive pooling (GCP) module is introduced to obtain the global features of the image. Second, a dispersion‐based clustering method, which can effectively evaluate the quality of clustering and discover potential patterns in the data is designed. This approach considers a wider context of sample‐level pairwise relationships for robust cluster affinity assessment. It effectively addresses challenges posed by imbalanced data distributions in complex situations. The above structures are connected through a clustering contrastive learning framework, which not only improves the discriminative power of features and the accuracy of clustering, but also solves the problem of inconsistent clustering updates. Experimental results on three public datasets demonstrate the superiority of our method over existing unsupervised re‐ID methods.

Model-Based Co-Clustering in Customer Targeting Utilizing Large-Scale Online Product Rating Networks

Given the widely available online customer ratings on products, the individual-level rating prediction and clustering of customers and products are increasingly important for sellers to create targeting strategies for expanding the customer base and improving product ratings. However, the massive missing data problem is a significant challenge for modeling online product ratings. To address this issue, we propose a new co-clustering methodology based on a bipartite network modeling of large-scale ordinal product ratings. Our method extends existing co-clustering methods by incorporating covariates and ordinal ratings in the model-based co-clustering of a weighted bipartite network. We devise an efficient variational EM algorithm for model estimation. A simulation study demonstrates that our methodology is scalable for modeling large datasets and provides accurate estimation and clustering results. We further show that our model can successfully identify different groups of customers and products with meaningful interpretations and achieve promising predictive performance in a real application for customer targeting.

Research on the Optimization of Ship Trajectory Clustering Based on the OD–Hausdorff Distance

With the growth of global trade, port shipping is becoming more and more important. In this paper, an analysis of a ship’s inbound and outbound track characteristics is conducted using the OD–Hausdorff distance. The accuracy and efficiency of trajectory data analysis have been enhanced through clustering analysis. Trajectories are arranged in a time sequence, and representative port segments are selected. An improved OD–Hausdorff distance method is employed to capture the dynamic characteristics of a ship’s movements, such as speed and heading. Additionally, the DBSCAN algorithm is utilized for clustering, allowing for the processing of multidimensional AIS data. Data cleaning and preprocessing have ensured the reliability of the AIS data, and the Douglas–Peucker algorithm is used for trajectory simplification. Significant improvements in the accuracy and efficiency of trajectory clustering have been observed. Therefore, the main channel of the Guan River and the right side of Yanwei Port are usually followed by ships greater than 60 m in length, with a lateral Relative Mean Deviation (RMD) of 7.06%. Vessels shorter than 60 m have been shown to have greater path variability, with a lateral RMD of 7.94%. Additionally, a crossing pattern at Xiangshui Port is exhibited by ships shorter than 60 m due to the extension of berths and their positions at turns. Enhanced clustering accuracy has provided more precise trajectory patterns, which aids in better channel management.

SPGMVC: Multiview Clustering via Partitioning the Signed Prototype Graph.

Multiview clustering (MVC) has been widely studied in machine learning and data mining for its capability of improving clustering performance by fusing the information from multiview data. In the past decade, a large number of MVC methods have made impressive progress, but most of them suffer from computational burdens, especially in large-scale tasks. Binary MVC (BMVC) is proposed to address this issue by representing the large-scale high-dimensional dataset as a group of consensus and low-dimensional binary codes. However, current BMVC-based approaches generate the clustering by executing binary k -means on the obtained binary codes, which fail to capture the embedded geometric information, leading to poor clustering performance. In addition, parameter selection is another "mission impossible" in unsupervised learning tasks including MVC. To tackle these challenges, a framework of multiview clustering via partitioning the signed prototype graph (SPGMVC) is proposed in this work. The SPGMVC framework offers several contributions. First, SPGMVC is designed as a unified framework for MVC. It combines effective technologies, such as consensus binary coding, code compression (CC), signed prototype graph (SPG) partitioning, and prototype-based cluster assignment. Second, SPGMVC partitions the signed graph (SG) based on the relationships between positive and negative edges. By capturing the underlying structure of the data, this partitioning strategy improves clustering accuracy (ACC). CC techniques are applied to reduce the graph's scale, enabling further partitioning and enhancing computational efficiency. Third, SPGMVC employs an alternate minimizing strategy to efficiently handle the optimization problem. This strategy has nearly linear time and space complexity with respect to the data volume, making it suitable for large-scale tasks. Fourth, SPGMVC proposes an automatic parameter selection strategy, eliminating the need for extensive parameter exploration. Comprehensive experiments illustrate the superiority of our model. The implementation of SPGMVC is available at: https://github.com/gepingyang/PSGMVC.

Multi-Objective Unsupervised Feature Selection and Cluster Based on Symbiotic Organism Search

Unsupervised learning is a type of machine learning that learns from data without human supervision. Unsupervised feature selection (UFS) is crucial in data analytics, which plays a vital role in enhancing the quality of results and reducing computational complexity in huge feature spaces. The UFS problem has been addressed in several research efforts. Recent studies have witnessed a surge in innovative techniques like nature-inspired algorithms for clustering and UFS problems. However, very few studies consider the UFS problem as a multi-objective problem to find the optimal trade-off between the number of selected features and model accuracy. This paper proposes a multi-objective symbiotic organism search algorithm for unsupervised feature selection (SOSUFS) and a symbiotic organism search-based clustering (SOSC) algorithm to generate the optimal feature subset for more accurate clustering. The efficiency and robustness of the proposed algorithm are investigated on benchmark datasets. The SOSUFS method, combined with SOSC, demonstrated the highest f-measure, whereas the KHCluster method resulted in the lowest f-measure. SOSFS effectively reduced the number of features by more than half. The proposed symbiotic organisms search-based optimal unsupervised feature-selection (SOSUFS) method, along with search-based optimal clustering (SOSC), was identified as the top-performing clustering approach. Following this, the SOSUFS method demonstrated strong performance. In summary, this empirical study indicates that the proposed algorithm significantly surpasses state-of-the-art algorithms in both efficiency and effectiveness. Unsupervised learning in artificial intelligence involves machine-learning techniques that learn from data without human supervision. Unlike supervised learning, unsupervised machine-learning models work with unlabeled data to uncover patterns and insights independently, without explicit guidance or instruction.

Multi-modal data clustering using deep learning: A systematic review

Multi-modal clustering represents a formidable challenge in the domain of unsupervised learning. The objective of multi-modal clustering is to categorize data collected from diverse modalities, such as audio, visual, and textual sources, into distinct clusters. These clustering techniques operate by extracting shared features across modalities in an unsupervised manner, where the identified common features exhibit high correlations within real-world objects. Recognizing the importance of perceiving the correlated nature of these features is vital for enhancing clustering accuracy in multi-modal settings. This survey explores Deep Learning (DL) techniques applied to multi-modal clustering, encompassing methodologies such as Convolutional Neural Networks (CNN), Autoencoders (AE), Recurrent Neural Networks (RNN), and Graph Convolutional Networks (GCN). Notably, this survey represents the first attempt to investigate DL techniques specifically for multi-modal clustering. The survey presents a novel taxonomy for DL-based multi-modal clustering, conducts a comparative analysis of various multi-modal clustering approaches, and deliberates on the datasets employed in the evaluation process. Additionally, the survey identifies research gaps within the realm of multi-modal clustering, offering insights into potential future avenues for research.

COMPARISON OF CORONA DISCHARGE IDENTIFICATION IN 20 kV CUBICLES BASED ON VOLTAGE AND NOISE USING ED, HMM, AND FCM

Phenomena such as corona discharge (CD) still occurs in many electrical systems in Indonesia. As a first step for early detection of insulation failure. Identification of CD acoustic in this study namely clustering based on voltage and based on noise. So that the CD acoustic classification is set into 3 clusters. In addition, this study also classifies CD acoustic based on noise with three clusters, namely pure CD, CD with noise, and pure noise. Clustering was performed using the linear predictive coding (LPC) method as feature extraction, then a comparison of pattern matching results of feature extraction was performed using Euclidean distance (ED), hidden Markov model (HMM) and fuzzy cluster mean (FCM). The temperature in the cubical is between 27.5 ℃ - 35.3 ℃ and humidity ranges from 70% - 95%. The results of clustering accuracy on the average base voltage using the ED, HMM and FCM methods were obtained respectively 100%, 100% 93.93% for training data and 80.74%, 84.44%, 80.55% for testing data. While the results of the average base noise clustering accuracy using the ED, HMM and FCM methods were obtained respectively 100%, 100%, 94.69% for training data and 100%, 100%, 100% for testing data.

Benchmarking clustering, alignment, and integration methods for spatial transcriptomics

BackgroundSpatial transcriptomics (ST) is advancing our understanding of complex tissues and organisms. However, building a robust clustering algorithm to define spatially coherent regions in a single tissue slice and aligning or integrating multiple tissue slices originating from diverse sources for essential downstream analyses remains challenging. Numerous clustering, alignment, and integration methods have been specifically designed for ST data by leveraging its spatial information. The absence of comprehensive benchmark studies complicates the selection of methods and future method development.ResultsIn this study, we systematically benchmark a variety of state-of-the-art algorithms with a wide range of real and simulated datasets of varying sizes, technologies, species, and complexity. We analyze the strengths and weaknesses of each method using diverse quantitative and qualitative metrics and analyses, including eight metrics for spatial clustering accuracy and contiguity, uniform manifold approximation and projection visualization, layer-wise and spot-to-spot alignment accuracy, and 3D reconstruction, which are designed to assess method performance as well as data quality. The code used for evaluation is available on our GitHub. Additionally, we provide online notebook tutorials and documentation to facilitate the reproduction of all benchmarking results and to support the study of new methods and new datasets.ConclusionsOur analyses lead to comprehensive recommendations that cover multiple aspects, helping users to select optimal tools for their specific needs and guide future method development.

Business English Teaching Reform Under the Background of Artificial Intelligence + Big Data

The level of information technology is increasing, and technology is developed. University English teaching has also changed under its influence. Different from the traditional teaching in the past, more and more students adopt the mode of “Internet + Smartphone” to learn English. This paper proposes a teaching mode evaluation method in the context of big data. Through the K-means algorithm based on it, the data clustering of business English teaching mode is completed. According to the data obtained from clustering, combined with the standardization of positive and negative indicators, the business English teaching mode system is constructed. Experiments show that when the clustering K value is 16, the clustering accuracy of this method is 99.2%, and it can effectively get the index weights, and the evaluation time is short, which is better than the other two comparison methods.

PSA-FL-CDM: A Novel Federated Learning-Based Consensus Model for Post-Stroke Assessment.

The rapid development of Internet of Things (IoT) technologies and the potential benefits of employing the vast datasets generated by IoT devices, including wearable sensors and camera systems, has ushered in a new era of opportunities for enhancing smart rehabilitation in various healthcare systems. Maintaining patient privacy is paramount in healthcare while providing smart insights and recommendations. This study proposed the adoption of federated learning to develop a scalable AI model for post-stroke assessment while protecting patients' privacy. This research compares the centralized (PSA-MNMF) model performance with the proposed scalable federated PSA-FL-CDM model for sensor- and camera-based datasets. The computational time indicates that the federated PSA-FL-CDM model significantly reduces the execution time and attains comparable performance while preserving the patient's privacy. Impact Statement-This research introduces groundbreaking contributions to stroke assessment by successfully implementing federated learning for the first time in this domain and applying consensus models in each node. It enables collaborative model training among multiple nodes or clients while ensuring the privacy of raw data. The study explores eight different clustering methods independently on each node, revolutionizing data organization based on similarities in stroke assessment. Additionally, the research applies the centralized PSA-MNMF consensus clustering technique to each client, resulting in more accurate and robust clustering solutions. By utilizing the FedAvg federated learning algorithm strategy, locally trained models are combined to create a global model that captures the collective knowledge of all participants. Comparative performance measurements and computational time analyses are conducted, facilitating a fair evaluation between centralized and federated learning models in stroke assessment. Moreover, the research extends beyond a single type of database by conducting experiments on two distinct datasets, wearable and camera-based, broadening the understanding of the proposed methods across different data modalities. These contributions develop stroke assessment methodologies, enabling efficient collaboration and accurate consensus clustering models and maintaining data privacy.

Multi-order graph clustering with adaptive node-level weight learning

Current graph clustering methods emphasize individual node and edge connections, while ignoring higher-order organization at the level of motif. Recently, higher-order graph clustering approaches have been designed by motif-based hypergraphs. However, these approaches often suffer from hypergraph fragmentation issue seriously, which degrades the clustering performance greatly. Moreover, real-world graphs usually contain diverse motifs, with nodes participating in multiple motifs. A key challenge is how to achieve precise clustering results by integrating information from multiple motifs at the node level. In this paper, we propose a multi-order graph clustering model (MOGC) to integrate multiple higher-order structures and edge connections at node level. MOGC employs an adaptive weight learning mechanism to automatically adjust the contributions of different motifs for each node. This not only tackles hypergraph fragmentation issue but enhances clustering accuracy. MOGC is efficiently solved by an alternating minimization algorithm. Experiments on seven real-world datasets illustrate the effectiveness of MOGC.

Selective multiple kernel fuzzy clustering with locality preserved ensemble

Multiple kernel fuzzy clustering (MKFC) has demonstrated promising performance in capturing the non-linear relationships within data. However, its effectiveness relies heavily on the appropriate selection of the fuzzification coefficient and kernel functions. To address this challenge, this paper proposes a novel clustering ensemble approach for improving the robustness and accuracy of the MKFC algorithm. The proposed method employs a multi-objective evolutionary optimization approach to heuristically select the optimal fuzzification and kernel coefficients. By employing the selected coefficients, the MKFC algorithm generates a diverse set of accurate candidate clustering results. Subsequently, a locality preserved ensemble mechanism is introduced to derive the final partition matrix, ensuring that all candidate clusterings within the Pareto non-dominated set contribute to the final consensus matrix. Moreover, this mechanism incorporates the knowledge about the locality of the dataset via a graph regularization term, thereby further enhancing the clustering performance. Comprehensive experiments conducted on widely adopted benchmark datasets demonstrate the superiority of the proposed method over the state-of-the-art approaches.

Beta Distribution Weighted Fuzzy C-Ordered-Means Clustering

The fuzzy C-ordered-means clustering (FCOM) is a fuzzy clustering algorithm that enhances robustness and clustering accuracy through the ordered mechanism based on fuzzy C-means (FCM). However, despite these improvements, the FCOM algorithm’s effectiveness remains unsatisfactory due to the significant time cost incurred by its ordered operation. To address this problem, an investigation was conducted on the ordered weighted model of the FCOM algorithm leading to proposed enhancements by introducing the beta distribution weighted fuzzy C-ordered-means clustering (BDFCOM). The BDFCOM algorithm utilises the properties of the Beta distribution to weight sample features, thus not only circumventing the time cost problem of the traditional ordered mechanism but also reducing the influence of noise. Experiments were conducted on six UCI datasets to validate the effectiveness of the BDFCOM, comparing its performance against seven other clustering algorithms using six evaluation indices. The results show that compared to the average of the other seven algorithms, BDFCOM improves about 15 percent on F1-score, 11 percent on Rand Index, 13 percent on Adjusted Rand Index, 3 percent on Fowlkes-Mallows Index and 16 percent on Jaccard Index. For the other two ordered mechanism FCM algorithms, the time consumption was also reduced by 90.15 percent on average. The proposed algorithm, which designs a new way of feature weighting for ordered mechanisms, advances the field of ordered mechanisms.And, this paper provides a new method in the application field where there is a lot of noise in the dataset.

Biomarker for infection in children with decompensated chronic liver disease: Neutrophilic CD64 or procalcitonin?

ObjectiveBiomarkers with high accuracy for identification of infection in decompensated chronic liver disease (DCLD) are urgently needed. We compared the accuracy of neutrophilic cluster of differentiation 64 (nCD64) with procalcitonin for diagnosis of bacterial infection in children with DCLD. MethodsConsecutive children admitted with DCLD were enrolled prospectively. nCD64 was assessed by flow cytometry and expressed in percentage. nCD64, procalcitonin and hemogram were measured at admission and 7-14 days after treatment in those with infection. Complete work-up for infection was done. Presence, site and severity of infection was classified as per guidelines. Results107 children [64 boys, age 97(18-168) months] were enrolled. 78(72.9%) had infection, 26(24%) had severe sepsis and 60(56%) had systemic inflammatory response syndrome. The commonest site of infection was ascitic fluid (n=37), followed by pneumonia (n=24), urinary tract (n=15), bacteraemia (n=10), cholangitis (n=8) and cellulitis (n=3). nCD64 (cut-off-51%, AUC-0.82) had a higher sensitivity (79.5%) and specificity (82.8%) than procalcitonin (cut-off ≥0.58ng/mL, AUC-0.74, sensitivity-76.9% and specificity-62.1%) for diagnosis of infection. nCD64 and procalcitonin correlated with infection severity, being highest in children with severe sepsis [88(71-97) %and 1.98(0.83-10.36) ng/mL], than in infection alone [72(45-84) % and 1.09(0.45-2.07) ng/mL], and no-infection [36(20.2-48) % and 0.42(0.19-1.08) ng/mL]. There was no difference in diagnostic utility of procalcitonin or nCD64 with different sites of infection. Elevation of all 3 parameters (nCD64, PCT and total leukocyte count) was uncommon but highly specific for presence of infection. ConclusionnCD64 identifies infection better than procalcitonin and correlates well with infection severity in children with DCLD.

Verification of acromion marker cluster and scapula spinal marker cluster methods for tracking shoulder kinematics: a comparative study with upright four-dimensional computed tomography

BackgroundThis study validated the accuracy of the acromion marker cluster (AMC) and scapula spinal marker cluster (SSMC) methods compared with upright four-dimensional computed tomography (4DCT) analysis.MethodsSixteen shoulders of eight healthy males underwent AMC and SSMC assessments. Active shoulder elevation was tracked using upright 4DCT and optical motion capture system. The scapulothoracic and glenohumeral rotation angles calculated from AMC and SSMC were compared with 4DCT. Additionally, the motion of these marker clusters on the skin with shoulder elevation was evaluated.ResultsThe average differences between AMC and 4DCT during 10°−140° of humerothoracic elevation were − 2.2° ± 7.5° in scapulothoracic upward rotation, 14.0° ± 7.4° in internal rotation, 6.5° ± 7.5° in posterior tilting, 3.7° ± 8.1° in glenohumeral elevation, − 8.3° ± 10.7° in external rotation, and − 8.6° ± 8.9° in anterior plane of elevation. The difference between AMC and 4DCT was significant at 120° of humerothoracic elevation in scapulothoracic upward rotation, 50° in internal rotation, 90° in posterior tilting, 120° in glenohumeral elevation, 100° in external rotation, and 100° in anterior plane of elevation. However, the average differences between SSMC and 4DCT were − 7.5 ± 7.7° in scapulothoracic upward rotation, 2.0° ± 7.0° in internal rotation, 2.3° ± 7.2° in posterior tilting, 8.8° ± 7.9° in glenohumeral elevation, 2.0° ± 9.1° in external rotation, and 1.9° ± 10.1° in anterior plane of elevation. The difference between SSMC and 4DCT was significant at 50° of humerothoracic elevation in scapulothoracic upward rotation and 60° in glenohumeral elevation, with no significant differences observed in other rotations. Skin motion was significantly smaller in AMC (28.7 ± 4.0 mm) than SSMC (38.6 ± 5.8 mm). Although there was smaller skin motion in AMC, SSMC exhibited smaller differences in scapulothoracic internal rotation, posterior tilting, glenohumeral external rotation, and anterior plane of elevation compared to 4DCT.ConclusionThis study demonstrates that AMC is more accurate for assessing scapulothoracic upward rotation and glenohumeral elevation, while SSMC is preferable for evaluating scapulothoracic internal rotation, posterior tilting, glenohumeral external rotation, and anterior plane of elevation, with smaller differences compared to 4DCT.

ScLEGA: an attention-based deep clustering method with a tendency for low expression of genes on single-cell RNA-seq data.

Single-cell RNA sequencing (scRNA-seq) enables the exploration of biological heterogeneity among different cell types within tissues at a resolution. Inferring cell types within tissues is foundational for downstream research. Most existing methods for cell type inference based on scRNA-seq data primarily utilize highly variable genes (HVGs) with higher expression levels as clustering features, overlooking the contribution of HVGs with lower expression levels. To address this, we have designed a novel cell type inference method for scRNA-seq data, termed scLEGA. scLEGA employs a novel zero-inflated negative binomial (ZINB) loss function that fully considers the contribution of genes with lower expression levels and combines two distinct scRNA-seq clustering strategies through a multi-head attention mechanism. It utilizes a low-expression optimized denoising autoencoder, based on the novel ZINB model, to extract low-dimensional features and handle dropout events, and a GCN-based graph autoencoder (GAE) that leverages neighbor information to guide dimensionality reduction. The iterative fusion of denoising and topological embedding in scLEGA facilitates the acquisition of cluster-friendly cell representations in the hidden embedding, where similar cells are brought closer together. Compared to 12 state-of-the-art cell type inference methods on 15 scRNA-seq datasets, scLEGA demonstrates superior performance in clustering accuracy, scalability, and stability. Our scLEGA model codes are freely available at https://github.com/Masonze/scLEGA-main.