Segmentation Scheme Research Articles

Real-Time Automatic M-Mode Echocardiography Measurement With Panel Attention.

Motion mode (M-mode) echocardiography is essential for measuring cardiac dimension and ejection fraction. However, the current diagnosis is time-consuming and suffers from diagnosis accuracy variance. This work resorts to building an automatic scheme through well-designed and well-trained deep learning to conquer the situation. That is, we proposed RAMEM, an automatic scheme of real-time M-mode echocardiography, which contributes three aspects to address the challenges: 1) provide MEIS, the first dataset of M-mode echocardiograms, to enable consistent results and support developing an automatic scheme; For detecting objects accurately in echocardiograms, it requires big receptive field for covering long-range diastole to systole cycle. However, the limited receptive field in the typical backbone of convolutional neural networks (CNN) and the losing information risk in non-local block (NL) equipped CNN risk the accuracy requirement. Therefore, we 2) propose panel attention embedding with updated UPANets V2, a convolutional backbone network, in a real-time instance segmentation (RIS) scheme for boosting big object detection performance; 3) introduce AMEM, an efficient algorithm of automatic M-mode echocardiography measurement, for automatic diagnosis; The experimental results show that RAMEM surpasses existing RIS schemes (CNNs with NL & Transformers as the backbone) in PASCAL 2012 SBD and human performances in MEIS.

Identifying Halos in Cosmological Simulations with Continuous Wavelet Analysis: The 2D Case

Continuous wavelet analysis is gaining popularity in science and engineering for its ability to analyze data across both spatial and scale domains simultaneously. In this study, we introduce a wavelet-based method for halo identification and assess its feasibility in two-dimensional (2D) scenarios. We begin by generating four pseudo-2D data sets from the SIMBA dark matter simulation by compressing thin slices of three-dimensional (3D) data into 2D. Subsequently, we calculate the continuous wavelet transform (CWT) directly from the particle distributions, identify local maxima that represent actual halos, and segment the CWT to delineate halo boundaries. A comparison with the traditional friends-of-friends (FOF) method shows that while our CWT-identified halos contain slightly fewer particles, they have smoother boundaries and are more compact in dense regions. In contrast, the CWT method can link particles over greater distances to form halos in sparse regions due to its spatial segmentation scheme. The spatial distribution and halo power spectrum of both CWT and FOF halos demonstrate substantial consistency, validating the 2D applicability of CWT for halo detection. While our identification scheme has been tested solely in a limited 2D context and has shown some performance limitations, its linear time complexity of O(N) and consistency with the FOF method suggest its suitability for analyzing significantly larger data sets in the future and its potential to be extended to the 3D case.

Topographical Quantification of Retinal Fluid in Type 3 MNV and Associations With Short-Term Visual Outcomes

PurposeThis study aims to quantify the volume of intraretinal fluid (IRF), subretinal fluid (SRF), and sub-retinal pigment epithelium (sub-RPE) fluid in treatment-naïve Type 3 macular neovascularization (MNV) eyes with age-related macular degeneration (AMD) and to investigate the correlation of these fluid volumes with visual acuity (VA) outcomes at baseline and following anti-vascular endothelial growth factor (VEGF) treatment. DesignRetrospective, clinical cohort study. MethodsIn this study, we analyzed patients diagnosed with exudative AMD and treatment-naïve Type 3 MNV undergoing a loading dose of anti-VEGF therapy. Using a validated deep-learning segmentation strategy, we processed optical coherence tomography (OCT) B-scans to segment and quantify IRF (i.e., both in the inner and outer retina), SRF, and sub-RPE fluid volumes at baseline. The study correlated baseline fluid volumes with baseline and short-term VA outcomes post-loading dose of anti-VEGF injections. ResultsForty-six eyes from 46 patients were included in this study. Visual acuity was 0.51±0.30 LogMAR at baseline and 0.33±0.20 LogMAR after the loading dose of anti-VEGF (p=0.001). Visual acuity at the follow-up visit was 0.40±0.17 LogMAR in patients with no complete resolution of retinal fluid and 0.31±0.20 LogMAR in eyes without retinal fluid after treatment (P=0.225). In the multivariable analysis, the IRF volume in the inner retina (P=0.032) and the distance of the MNV from the fovea (P=0.037) were predictors of visual acuity at baseline. The baseline IRF volume in the inner retina also predicted the visual acuity at follow-up (p=0.023). ConclusionThe present study highlights the fluid volume in the inner retina as a crucial predictor of short-term visual outcomes in Type 3 MNV, underscoring the detrimental effect of IRF on neuroretinal structures.

Research on Automobile User Labeling Library Based on Factor Analysis

The purpose of this paper is to explore in-depth the demographic characteristics of automobile users of luxury brands, traditional joint-venture brands, traditional independent brands, new brands of traditional automobile enterprises and new power brands, as well as the differences and commonalities of their attitude on automobile consumpt by means of a questionnaire survey. First, statistical methods were used to analyze and reveal the significant differences in basic characteristics between different brands of automobile users, such as comparing and finding significant differences in income levels between luxury brand users and independent brand users. Secondly, through the factor analysis technique, a few representative factors are extracted from the complicated conceptual descriptors to simplify and clearly present the core dimensions of attitude on automobile consumpt of users of different brands, so as to provide a scientific basis for automobile manufacturers to formulate market segmentation and marketing strategies.

Cross-cultural Marketing: Analysis of Marketing Strategies and Consumer Behavior Under Different Cultural Backgrounds

The marketing strategy and consumption behavior of the intelligent board writing software in the cross-cultural market are deeply discussed. Based on the analysis of market demand and consumption habits under different cultural backgrounds, various effective marketing strategies of cross-cultural market are put forward. First, in order to better meet the needs of users in different regions, the importance of language localization and cultural adaptation is emphasized. Secondly, according to the needs of different brand image and marketing methods under different cultural backgrounds, the brand positioning and market segmentation strategy are discussed, and it is pointed out that there need to be different. Finally, according to the specific measures of increasing the market share and brand influence of intelligent board book software, the selection of online and offline marketing channels is analyzed, combined with the purchasing motivation and use habits of consumers.

Methodological Approaches to Optical Disc and Optical Cup Segmentation: A Critical Assessment

A progressive optic nerve condition called glaucoma causes irreversible eyesight loss. To diagnose retinal diseases, retinal fundus imaging has been used in recent years. Analyzing these images effectively requires pinpointing the areas of interest, which can be tricky, due to the anatomy and vascular patterns in fundus images. Different image segmentation techniques are used to extract the area of interest from the fundus images. This paper explores the various segmentation methodologies, emphasizing conventional and modern retinal fundus image segmentation approaches. Evaluation measures such as the Disc damage likelihood scale, Inferior superior temporal region, Dice similarity coefficient, Jaccard index, Sensitivity and Specificity are used to measure the effectiveness of segmentation algorithms, which detect small structural changes that indicate glaucomatous damage. Furthermore, this paper also provides a detailed analysis of deep learning algorithms used for optic cup and optic disc segmentation. This detailed analysis demonstrates that accurate disc and cup segmentation remains a significant challenge and suggests that effective segmentation strategies and deep learning approaches are required for vast and complex datasets.

Nearest neighbors and density-based undersampling for imbalanced data classification with class overlap

While addressing the problem of imbalanced data classification, most existing resampling methods primarily focus on balancing class distribution. However, they often overlook class overlap and fail to adequately consider the feature distributions of different classes. Consequently, when resampling is performed under such conditions, samples within areas of overlap remain susceptible to misclassification, failing to substantially improve overall performance. To address these shortcomings, we propose a novel data resampling technique, Nearest Neighbors and Density-based Undersampling (NDU). This method employs within-class k-nearest neighbors and between-class probability densities to design a weight assignment strategy. Leveraging this strategy, we establish an exclusive metric, the F_factor, to evaluate the importance of majority class samples in overlap areas. Subsequently, NDU promotes a gradient-based segmented undersampling strategy, which applies varying degrees of undersampling to majority class samples across segmented regions. Through experiments on binary imbalanced datasets with class overlap, we evaluate the efficiency of diverse resampling methods concerning classification performance. The results demonstrate that our proposed method effectively addresses class overlap challenges.

Image Multi-threshold Segmentation Based on an Ameliorated Harmony Search Optimization Algorithm

Image segmentation is the basis and premise of image processing, though traditional multi-threshold image segmentation methods are simple and effective, they suffer the problems of low accuracy and slow convergence rate. For that reason, this paper introduces the multi-threshold image segmentation scheme by combining the harmony search (HS) optimization algorithm and the maximum between-class variance (Otsu) to solve them. Firstly, to further improve the performance of the basic HS, an ameliorated harmony search (AHS) is put forward by modifying the generation method of the new harmony improvisation and introducing a convergence coefficient. Secondly, the AHS algorithm, which takes the maximum between-class variance as its objective function, namely AHS-Otsu, is applied to image multi-level threshold segmentation. Finally, six test images are selected to verify the multilevel segmentation performance of AHS-Otsu. Peak signal-to-noise ratio (PSNR) and structural similarity index (SSIM) are two commonly used metrics for evaluating the effectiveness of image segmentation, which are both used in this article. Comprehensive experimental results indicate that the AHS-Otsu does not only has fast segmentation processing speed, but also can obtain more accurate segmentation performance than others, which prove the effectiveness and potential of the AHS-Otsu algorithm in the field of image segmentation especially for the multi-threshold.

FELC-SLAM: feature extraction and loop closure optimized lidar SLAM system

Abstract Simultaneous Localization and Mapping (SLAM) is one of the key technologies in robot navigation and autonomous driving, playing an important role in robot navigation. Due to the sparsity of LiDAR data and the singularity of point cloud features, accuracy loss of LiDAR SLAM can occur during point cloud matching and localization. In response to these issues, this paper proposes a LiDAR Measurement SLAM algorithm that integrates multi type geometric feature extraction and optimized point cloud registration algorithms. This article first adopts advanced ground segmentation methods and feature segmentation strategies, including ground features, edge features, planar features, and spherical features, to improve matching accuracy. In addition, this article improves the previous method for extracting edge and planar features, extracting clearer and more robust line and surface features to address the degradation of geometric features. Finally, by introducing a robust decoupling global registration method for loop closure detection in the backend of the system, the sparsity problem of distant point clouds and the degradation problem caused by the reduction of inner layers in point cloud registration were effectively solved. In the evaluation of the KITTI dataset, our algorithm reduced absolute trajectory error values by 60%, 29%, and 71% compared to LeGO-LOAM in multi loop and feature constrained scenarios (such as sequences 00, 01, and 02), respectively. The evaluation of the M2DGR and Botanic Garden datasets also indicates that the positioning accuracy of our algorithm is superior to other advanced LiDAR SLAM algorithms.

Multi-Agent Collaborative Path Planning Algorithm with Multiple Meeting Points

Traditional multi-agent path planning algorithms often lead to path overlap and excessive energy consumption when dealing with cooperative tasks due to the single-agent-single-task configuration. For this reason, the “many-to-one” cooperative planning method has been proposed, which, although improved, still faces challenges in the vast search space for meeting points and unreasonable task handover locations. This paper proposes the Cooperative Dynamic Priority Safe Interval Path Planning with a multi-meeting-point and single-meeting-point solving mode switching (Co-DPSIPPms) algorithm to achieve multi-agent path planning with task handovers at multiple or single meeting points. First, the initial priority is set based on the positional relationships among agents within the cooperative group, and the improved Fermat point method is used to locate multiple meeting points quickly. Second, considering that agents must pick up sub-tasks or conduct task handovers midway, a segmented path planning strategy is proposed to ensure that cooperative agents can efficiently and accurately complete task handovers. Finally, an automatic switching strategy between multi-meeting-point and single-meeting-point solving modes is designed to ensure the algorithm’s success rate. Tests show that Co-DPSIPPms outperforms existing algorithms in 1-to-1 and m-to-1 cooperative tasks, demonstrating its efficiency and practicality.

Construction of scalable multi-channel DNA nanoplatform for the combined detection of ctDNA biomarkers of ovarian cancer.

Single-level biomarker detection has the limitation of insufficient accuracy in cancer diagnosis. Therefore, the strategy of developing highly sensitive, multi-channel biosensors for high-throughput ctDNAdetermination is critical to improve the accuracy of early diagnosis of clinical tumors. Herein, in order to achieve efficient detection of up to ten targets for early diagnosis of ovarian cancer, a DNA-nanoswitch-based multi-channel (DNA-NSMC) biosensor was built based on the multi-module catalytic hairpin assembly-mediated signal amplification (CHA) and toehold-mediated DNA strand displacement (TDSD) reaction. Only two different fluorescence signals were used as outputs, combined with modular segmentation strategy of DNA-nanoswitch-based reaction platform; the multi-channel detection of up to ten targets was successfully achieved for the first time. The experimental results suggest that the proposed biosensor is a promising tool for simultaneously detecting multiple biomarkers for the early diagnosis of ovarian cancer, offering new strategies for the early screening, diagnosis, and treatment not only for ovarian cancer but also for other cancers.

Market Segmentation Strategies: Analysis, Practice, and Marketing Implications

The article’s purpose has been to conduct a thorough and analytical review of the academic literature on market segmentation and consumer behavior to unearth emerging issues and trends. The paper begins a brief background on the concept of segmentation and a presentation of the objectives of the article. This is followed by the research methodology used. Next, the article assessed the relevant theoretical framework that underpins segmentation strategies and models. Then, the paper presents a rigorous analysis and synthesis of the extant empirical literature on market segmentation. This is followed by a discussion of emerging trends and issues in the area of market segmentation derived from the literature review. Lastly, the article outlines implications for marketing managers and provides recommendations for action.

Study on the application of a segmented sodium citrate solution anticoagulation strategy in critically ill patients receiving CRRT: a prospective, randomized controlled study

BackgroundTo explore the feasibility and effectiveness of a segmented sodium citrate solution anticoagulation strategy in patients receiving CRRT.MethodsA prospective, randomized controlled study was conducted.ResultsAccording to the inclusion and exclusion criteria, 80 patients were included and randomly divided into two groups. Moreover, coagulation indices, liver function indices, renal function indices, and SOFA and APACHE II scores did not significantly differ between the two groups (P > 0.05). The coagulation grade of the venous ports in the experimental group was lower than that in the control group and the two groups of filters, but the difference was not statistically significant (P = 0.337). Both sodium citrate solution infusion methods maintained a low blood calcium concentration (0.25–0.45 mmol/L) in the peripheral circulation pathway, and no patient developed hypocalcaemia (< 1.0 mmol/L). The lifespans of the extracorporeal circulation tube in the experimental group and the control group were 69.43 ± 1.49 h and 49.39 ± 2.44 h, respectively (t = 13.316, P = 0.001).ConclusionThe segmented citrate solution anticoagulation strategy could extend the lifespan of the extracorporeal circulation tube and improve CRRT efficacy.Trial registrationThe Chinese Clinical Trial Registry number is ChiCTR2200057272. Registered on March 5, 2022.

Research on positioning control strategy of hydraulic support pushing system based on multistage speed control valve

The precise position control of the hydraulic support pushing system in the coal mining face is a key technical support for intelligent coal mining. At present, the hydraulic support pushing system uses the electro-hydraulic directional valve as the control element. However, the electro-hydraulic directional valve has problems such as discrete input values, low switching frequency, delay, inability to adjust flow, and large flow fluctuations during the switching process, which results in relatively low positioning control accuracy of the hydraulic support pushing system. Therefore, this study introduces a multi-stage speed control valve that is suitable for underground coal mine conditions and can achieve flow regulation. At the same time, a segmented control strategy combining Bang-Bang control and online predictive control is proposed. Bang-bang control is used for fast propulsion with large flow rate, large range, and short time. Online predictive control method is used to achieve precise positioning control with small flow rate and small range, thereby solving the problem of low positioning control accuracy caused by the imperfect characteristics of electro-hydraulic directional valves. Finally, this study verified the effectiveness of the proposed scheme through simulation and experiments. The results showed that compared with existing logic positioning control methods based on electro-hydraulic directional valves, the proposed scheme can improve the accuracy of single cylinder positioning control from 62 mm to within 10 mm.

Market segmentation strategy, target markets, and competitors: a resource-advantage theory perspective

ABSTRACT Given that marketing managers are taught the significance of predicting and responding to competitors’ actions, comparing their firms’ strategies to those of competitors, and developing sustainable competitive advantages over competitors, the task of identifying competitors emerges as pivotal for effective marketing strategy development. However, a notable challenge lies in the diverse interpretations of what defines a competitor among strategists. This article explicates the nature of competitors by drawing on resource-advantage theory and its focus on market segments. Specifically, it focuses on market segmentation strategy as a mechanism to examine what constitutes a ‘competitor’. In addition, it outlines an approach that can be used to identify competitors.

Flotation froth image enhancement based on region decomposition and guided filtering

Extraction of information from froth images is important for automatic control of froth flotation. However, images captured by cameras often suffer from severe uneven lighting, which significantly reduces the quality of froth images. Low-quality images hinder the accurate extraction of froth information, thereby affecting the control of the froth flotation system. Hence, we propose an image enhancement method based on region decomposition and guided filtering to improve the quality of images. Initially, we separate the image into regions with sufficient and insufficient illumination based on reflectance. In regions with insufficient illumination, the guided filter is applied to direct pixels to acquire information from brighter points in their neighborhood. Conversely, in other regions, we regulate the magnitude of pixel variations to prevent overexposure. Finally, a detail enhancement method is proposed based on a multi-scale Gaussian pyramid and texture fusion to improve clarity and naturalness. The experiments show that the method we proposed surpasses several state-of-the-art algorithms on public datasets. In the field of flotation, our method effectively enhances the image quality. Compared to other enhancement methods under the same segmentation strategy, our method significantly improves segmentation accuracy, demonstrating its strong practical value. In addition, our method also shows advantages in terms of computational speed.

A multi-channel spatial information feature based human pose estimation algorithm

Human pose estimation is an important task in computer vision, which can provide key point detection of human body and obtain bone information. At present, human pose estimation is mainly utilized for detection of large targets, and there is no solution for detection of small targets. This paper proposes a multi-channel spatial information feature based human pose (MCSF-Pose) estimation algorithm to address the issue of medium and small targets inaccurate detection of human key points in scenarios involving occlusion and multiple poses. The MCSF-Pose network is a bottom-up regression network. Firstly, an UP-Focus module is designed to expand the feature information while reducing parameter computation during the up-sampling process. Then, the channel segmentation strategy is adopted to cut the features, and the feature information of multiple dimensions is retained through different convolutional groups, which reduces the parameter lightweight network model and makes up for the loss of the feature information associated with the depth of the network. Finally, the three-layer PANet structure is designed to reduce the complexity of the model. With the aid of the structure, it also to improve the detection accuracy and anti-interference ability of human key points. The experimental results indicate that the proposed algorithm outperforms YOLO-Pose and other human pose estimation algorithms on COCO2017 and MPII human pose datasets.

Surface fatigue crack segmentation in steel box girder bridges using an improved Unet convolutional neural network

Despite the success of crack segmentation, the traditional segmentation strategy and networks are not necessarily suitable for fatigue cracks with unique visual features. Towards the indistinct crack features, a network named Fatigue Crack Unet (FC-Unet) was proposed, where the novel split attention mechanism was incorporated to boost diverse feature extraction. Scaled by various ratios, raw images were cropped and constituted three datasets to represent different segmentation strategies. FC-Unet was trained and tested on each dataset, where the class imbalance problem was alleviated by the adjustment of loss functions. Results showed that the segmentation performance is mainly limited to noise interference. Preserving abundant global contexts to distinguish noises, the global inference is the superior strategy to the previous local inference. Leveraging the wide receptive field in global inference, the down-sampling rate can be decreased to save resolution losses. Combining the focus-based and region-based loss functions, the accuracy of imbalanced data was further improved. Compared with nine classical networks, the proposed FC-Unet enjoyed a powerful backbone and achieved a superior metric of 83.1% mean intersection over union (MIoU).

Operando study of the dynamic evolution of multiple Fe-rich intermetallics of an Al recycled alloy in solidification by synchrotron X-ray and machine learning

Using synchrotron X-ray diffraction, tomography and machine-learning enabled phase segmentation strategy, we have studied under operando conditions the nucleation, co-growth and dynamic interplays among the dendritic and multiple intermetallic phases of a typical recycled Al alloy (Al5Cu1.5Fe1Si, wt.%) in solidification with and without ultrasound. The research has revealed and elucidated the underlying mechanisms that drive the formation of the very complex and convoluted Fe-rich phases with rhombic dodecahedron and 3D skeleton networks (the so-called Chinese-script type morphology). Through statistical microstructural analyses and numerical modelling of the ultrasound melt processing, the research has demonstrated that a short period of ultrasound processing of just 7 s in the liquid state is able to reduce the average size of the α-Al dendrites and the Fe-containing intermetallic phases by ∼5 times compared to the cases without ultrasound. For the first time, this work has revealed fully the nucleation and growth dynamics of the convoluted morphology of the Fe-containing intermetallic phases in 4D domain. The research has also demonstrated clearly the beneficial effects of applying ultrasound to control the Fe phases' morphology in recycled Al alloys and it is one of the most effective and green processing strategies.

Improved allele-specific single-cell copy number estimation in low-coverage DNA-sequencing.

Advances in whole-genome single-cell DNA sequencing (scDNA-seq) have led to the development of numerous methods for detecting copy number aberrations (CNAs), a key driver of genetic heterogeneity in cancer. While most of these methods are limited to the inference of total copy number, some recent approaches now infer allele-specific CNAs using innovative techniques for estimating allele-frequencies in low coverage scDNA-seq data. However, these existing allele-specific methods are limited in their segmentation strategies, a crucial step in the CNA detection pipeline. We present SEACON (Single-cell Estimation of Allele-specific COpy Numbers), an allele-specific copy number profiler for scDNA-seq data. SEACON uses a Gaussian Mixture Model to identify latent copy number states and breakpoints between contiguous segments across cells, filters the segments for high-quality breakpoints using an ensemble technique, and adopts several strategies for tolerating noisy read-depth and allele frequency measurements. Using a wide array of both real and simulated datasets, we show that SEACON derives accurate copy numbers and surpasses existing approaches under numerous experimental conditions, and identify its strengths and weaknesses. SEACON is implemented in Python and is freely available open-source from https://github.com/NabaviLab/SEACON and https://doi.org/10.5281/zenodo.12727008.