Unsupervised K-means Research Articles

Application of machine learning for identification of heterotic groups in sunflower through combined approach of phenotyping, genotyping and protein profiling

Application of machine learning in plant breeding is a recent concept, that has to be optimized for precise utilization in the breeding program of high yielding crop plants. Identification and efficient utilization of heterotic grouping pattern aided with machine learning approaches is of utmost importance in hybrid cultivar breeding as it can save time and resources required to breed a new plant hybrid/variety. In the present study, 109 genotypes of sunflower were investigated at morphological, biochemical (SDS-PAGE) and molecular levels (through micro-satellites (SSR) markers) for heterotic grouping. All the three datasets were combined, scaled, and subjected to unsupervised machine learning algorithms, i.e., Hierarchical clustering, K-means clustering and hybrid clustering algorithm (hierarchical + K-means) for assessment of efficiency and resolution power of these algorithms in practical plant breeding for heterotic grouping identification. Following the application of machine learning unsupervised clustering approach, two major groups were identified in the studied sunflower germplasm, and further classification revealed six smaller classes in each major group through hierarchical and hybrid clustering approach. Due to high resolution, obtained in hierarchical clustering, classification achieved through this algorithm was further used for selection of potential parents. One genotype from each smaller group was selected based on the maximum seed yield potential and hybridized in a line × tester mating design producing 36 F1 cross combinations. These F1s along with their parents were studied in open field conditions for validating the efficacy of identified heterotic groups in sunflowers genetic material under study. Data for 11 agronomic and qualitative traits were recorded. These 36 F1 combinations were tested for their combining ability (General/Specific), heterosis, genotypic and phenotypic correlation and path analysis. Results suggested that F1 hybrids performed better for all the traits under investigation than their respective parents. Findings of the study validated the use of machine learning approaches in practical plant breeding; however, more accurate and robust clustering algorithms need to be developed to handle the data noisiness of open field experiments.

Using a k-means clustering to identify novel phenotypes of acute ischemic stroke and development of its Clinlabomics models.

Acute ischemic stroke (AIS) is a heterogeneous condition. To stratify the heterogeneity, identify novel phenotypes, and develop Clinlabomics models of phenotypes that can conduct more personalized treatments for AIS. In a retrospective analysis, consecutive AIS and non-AIS inpatients were enrolled. An unsupervised k-means clustering algorithm was used to classify AIS patients into distinct novel phenotypes. Besides, the intergroup comparisons across the phenotypes were performed in clinical and laboratory data. Next, the least absolute shrinkage and selection operator (LASSO) algorithm was used to select essential variables. In addition, Clinlabomics predictive models of phenotypes were established by a support vector machines (SVM) classifier. We used the area under curve (AUC), accuracy, sensitivity, and specificity to evaluate the performance of the models. Of the three derived phenotypes in 909 AIS patients [median age 64 (IQR: 17) years, 69% male], in phenotype 1 (N = 401), patients were relatively young and obese and had significantly elevated levels of lipids. Phenotype 2 (N = 463) was associated with abnormal ion levels. Phenotype 3 (N = 45) was characterized by the highest level of inflammation, accompanied by mild multiple-organ dysfunction. The external validation cohort prospectively collected 507 AIS patients [median age 60 (IQR: 18) years, 70% male]. Phenotype characteristics were similar in the validation cohort. After LASSO analysis, Clinlabomics models of phenotype 1 and 2 were constructed by the SVM algorithm, yielding high AUC (0.977, 95% CI: 0.961-0.993 and 0.984, 95% CI: 0.971-0.997), accuracy (0.936, 95% CI: 0.922-0.956 and 0.952, 95% CI: 0.938-0.972), sensitivity (0.984, 95% CI: 0.968-0.998 and 0.958, 95% CI: 0.939-0.984), and specificity (0.892, 95% CI: 0.874-0.926 and 0.945, 95% CI: 0.923-0.969). In this study, three novel phenotypes that reflected the abnormal variables of AIS patients were identified, and the Clinlabomics models of phenotypes were established, which are conducive to individualized treatments.

How Concerted Are Ionic Hops in Inorganic Solid-State Electrolytes?

Despite being fundamental to the understanding of solid-state electrolytes (SSEs), little is known on the degree of coordination between mobile ions in diffusive events, thus hindering a detailed comprehension and possible rational design of SSEs. Here, we introduce an unsupervised k-means clustering approach that is able to identify ion-hopping events and correlations between many mobile ions and apply it to a comprehensive ab initio MD database comprising several families of inorganic SSEs and millions of ionic configurations. It is found that despite two-body interactions between mobile ions being the largest, higher-order n-ion (2 < n) correlations are most frequent. Specifically, we prove a general exponential decaying law for the probability density function governing the number of concerted mobile ions. For the particular case of Li-based SSEs, it is shown that the average number of correlated mobile ions amounts to 10 ± 5 and that this result is practically independent of the temperature. Interestingly, our data-driven analysis reveals that fast-ionic diffusion strongly and positively correlates with ample hopping lengths and long hopping spans but not with high hopping frequencies and short interstitial residence times. Finally, it is shown that neglection of many-ion correlations generally leads to a modest overestimation of the hopping frequency that roughly is proportional to the average number of correlated mobile ions.

Prescreening bank failures with K-means clustering: Pros and cons

To study the merits of the popular K-means clustering technique while predicting failures of commercial banks, we contrast hereafter two forecasting systems. The first one contains two complementary stages, with unsupervised K-means clustering followed by logistic regression deployed over the three most hazardous clusters (out of five) formed. The second system incorporates logistic regression over the entire sample of banks. We find that the first prognostic system is relatively strict. It better identifies bank failures beforehand, but it also projects more potential failures among the solvent banks. The second system is more lenient. It does not identify in advance actual bank failures in many cases, yet it does not speculate failures for many solvent banks either. The second system achieves a slightly higher overall predictive power than the first system. The minor statistical disadvantage of the K-means clustering is observed mainly because of the scarcity of bank failures in practice. The K-means clustering prescreening stage intensifies the systemic costs associated with type-II errors (predicting failures for solvent banks), but it simultaneously reduces the systemic costs linked to type-I errors (not predicting failures for eventually failed banks). Overall, the K-means clustering prescreening technique has prospective economic advantages, as it assists in slashing the total simulated systemic costs.

Radiology Image Data Augmentation and Image Enhancement in Respiratory Disease Infection Detection Using Machine Learning Approach

Medical imaging plays an important role in medical diagnosis and treatment. It is also useful in medical applications. The proposed concept's goal is to understand the importance of data balancing, data augmentation, and segmentation in the clinical field, to improve image data balancing using data augmentation and edge detection techniques, to improve radiology image preprocessing to locate regions of interest (ROI), and to construct custom-built Deep Neural Networks (DNN) in diagnosing respiratory illness using Machine Learning approaches. Images of varying quality from multiple machine types are frequently included in different datasets. This study used four datasets, three of which are online datasets from Kaggle and the fourth is real-time radiology pictures of COVID and Pneumonia-infected persons from neighboring local hospitals. We proposed RESP_DATA_BALANCE for image data balance in dataset construction, and RDD_ROI (Respiratory Disease Detection Region of Interest) algorithm, which combines improved image feature extraction technique using a GLCM and unsupervised K-means clustering for segmentation to identify the region of interest in the detection of respiratory diseases. Our suggested custom-built 28-layer Respiratory Disease Detection Deep Neural Network (RDD_DNN) is used for further training, testing, and validation. Furthermore, experimental results focus on performance characteristics using various data augmentation, edge detection, and preprocessing strategies. The experimental purpose of our research study is to aid in the classification and early diagnosis of respiratory disorders.

Potential of K-means clustering for preliminary labeling of acoustic data samples

Labeling data for use in supervised learning algorithms can be a long and arduous process, especially for large datasets. This work explores if an unsupervised k-means clustering algorithm can act as a tool to efficiently obtain preliminary labels for large acoustic datasets. This approach is tested on vector sensor data from Monterey Accelerated Research System (MARS). To determine the optimal number of clusters in the k-means algorithm, the silhouette method is used. The clustering of different types of input data will be compared. Specifically, time average spectra from the pressure sensor, the acoustic particle velocity, and intensity will be considered. In addition, the results of clustering data from different times of day and months over a two-year period will be compared. Results of the clustering will be presented along with an assessment of the potential for using a k-means clustering as a preliminary labeling tool for large acoustic sets. [Undergraduate research funded by the College of Physical and Mathematical Sciences as Brigham Young University.]

Spatial transcriptomics reveals alterations in perivascular macrophage lipid metabolism in the onset of Wooden Breast myopathy in broiler chickens

This study aims to use spatial transcriptomics to characterize the cell-type-specific expression profile associated with the microscopic features observed in Wooden Breast myopathy. 1 cm3 muscle sample was dissected from the cranial part of the right pectoralis major muscle from three randomly sampled broiler chickens at 23 days post-hatch and processed with Visium Spatial Gene Expression kits (10X Genomics), followed by high-resolution imaging and sequencing on the Illumina Nextseq 2000 system. WB classification was based on histopathologic features identified. Sequence reads were aligned to the chicken reference genome (Galgal6) and mapped to histological images. Unsupervised K-means clustering and Seurat integrative analysis differentiated histologic features and their specific gene expression pattern, including lipid laden macrophages (LLM), unaffected myofibers, myositis and vasculature. In particular, LLM exhibited reprogramming of lipid metabolism with up-regulated lipid transporters and genes in peroxisome proliferator-activated receptors pathway, possibly through P. Moreover, overexpression of fatty acid binding protein 5 could enhance fatty acid uptake in adjacent veins. In myositis regions, increased expression of cathepsins may play a role in muscle homeostasis and repair by mediating lysosomal activity and apoptosis. A better knowledge of different cell-type interactions at early stages of WB is essential in developing a comprehensive understanding.

Intellectual development in young children with autism spectrum disorders: A longitudinal study.

Intelligence profiles in autism have been characterized by great variability. The questions of how autistic children's intelligence changes over time, and what factors influence these changes deserve study as part of efforts to document child autism profiles, but also because the relationship between intellectual functioning and children's background characteristics is poorly understood, particularly in a longitudinal context. A total of 39 autistic children and 39 age-matched neurotypical children (5-9 years old) completed two IQ assessments at preschool age and up to 4 years later. Repeated-measures analyses assessed longitudinal changes in the children's verbal (VIQ), performance (PIQ), and full-scale IQ (FSIQ) at group level. We further sought to identify clusters with distinct profiles in each group by adopting an unsupervised K-means clustering approach, and detect possible between-subgroup differences in terms of children's socioeconomic status and autism severity. The largest cluster in the autistic group was composed of children whose PIQ significantly dropped at follow-up, while the second largest cluster improved in all quotients; the smallest cluster, wherein children had more highly educated mothers than the rest of the clusters, was characterized by large improvement in VIQ. For the neurotypical children, there was a two-cluster division; the majority of them improved in the three quotients, while very few dropped in PIQ at follow-up. The relation between socioeconomic status and IQ changes was significant for both groups. The findings demonstrate both the complexity of intelligence changes in autism and the need to view this complexity through the lens of the children's socioeconomic diversity.

Unsupervised K-means Analysis of Tuberculosis Data in Brazil: Identifying High Prevalence States and Temporal Trends

This paper aims to demonstrate the findings obtained through the analysis and application of an unsupervised K-means algorithm on the SINAN database from 2001 to 2022 in Brazil, with the objective of understanding which states have the highest number of tuberculosis cases and identifying similarities among them that may contribute to a higher case rate relative to the local population. We will begin with a brief historical introduction, followed by an overview of the characteristics related to tuberculosis transmission. Subsequently, we will discuss the results obtained from the year-to-year analysis of the collected data.

Machine-learning-guided quantitative delineation of cell morphological features and responses to nanomaterials.

Delineation of cell morphological features is essential to decipher cell responses to external stimuli like theranostic nanomaterials. Conventional methods rely on labeled approaches, such as fluorescence imaging and flow cytometry, to assess cell responses. Besides potentially perturbing cell structure and morphology, these approaches are relatively complex, time-consuming, expensive, and may not be compatible with downstream analysis involving live cells. Herein, leveraging label-free phase-contrast or brightfield microscopy imaging and machine learning, the delineation of different cell types, phenotypes, and states for monitoring live cell responses is reported. Notably, pixel classification based on a supervised random forest classifier is used to distinguish between cells and backgrounds from the microscopy images, followed by cell segmentation and morphological feature extraction. Quantitative analysis shows that most of the compared cell groups have distinguishable size and shape features. Principal component analysis and unsupervised k-means clustering of morphological features reveal the possible existence of heterogenous cell subpopulations and treatment responses among the seemingly homogenous cell groups. This shows the merit of the reported approach in complementing conventional techniques for cell analysis. It is anticipated that the demonstrated method will further aid the implementation of machine learning to streamline the analysis of cell morphology and responses for early disease diagnosis and treatment response monitoring.

The immune landscape of sepsis and using immune clusters for identifying sepsis endotypes.

The dysregulated immune response to sepsis still remains unclear. Stratification of sepsis patients into endotypes based on immune indicators is important for the future development of personalized therapies. We aimed to evaluate the immune landscape of sepsis and the use of immune clusters for identifying sepsis endotypes. The indicators involved in innate, cellular, and humoral immune cells, inhibitory immune cells, and cytokines were simultaneously assessed in 90 sepsis patients and 40 healthy controls. Unsupervised k-means cluster analysis of immune indicator data were used to identify patient clusters, and a random forest approach was used to build a prediction model for classifying sepsis endotypes. We depicted that the impairment of innate and adaptive immunity accompanying increased inflammation was the most prominent feature in patients with sepsis. However, using immune indicators for distinguishing sepsis from bacteremia was difficult, most likely due to the considerable heterogeneity in sepsis patients. Cluster analysis of sepsis patients identified three immune clusters with different survival rates. Cluster 1 (36.7%) could be distinguished from the other clusters as being an "effector-type" cluster, whereas cluster 2 (34.4%) was a "potential-type" cluster, and cluster 3 (28.9%) was a "dysregulation-type" cluster, which showed the lowest survival rate. In addition, we established a prediction model based on immune indicator data, which accurately classified sepsis patients into three immune endotypes. We depicted the immune landscape of patients with sepsis and identified three distinct immune endotypes with different survival rates. Cluster membership could be predicted with a model based on immune data.

Decoding Human Somatosensory Sensitivity Through Resting EEG and Behavioral Analysis: A Multimodal Fusion Approach.

In precision medicine and clinical pain management, the creation of quantitative, objective indicators to assess somatosensory sensitivity was essential. This study proposed a fusion approach for decoding human somatosensory sensitivity, which combined multimodal (quantitative sensory test and neurophysiology) features to classify the dataset on individual somatosensory sensitivity and reveal distinct types of brain activation patterns. Sixty healthy participants took part in the experiment on somatosensory sensitivity that implemented cold, heat, mechanical punctate, and pressure stimuli, and the resting-state electroencephalography (EEG) was collected using BrainVision. The quantitative sensory testing (QST) scores of the participants were clustered using the unsupervised k-means algorithm into four subgroups: generally hypersensitive (HS), generally non-sensitive (NS), predominantly thermally sensitive (TS), and predominantly mechanically sensitive (MS). Furthermore, two types of power spectral density (PSD), band-based PSD (BB-PSD) and frequency-based PSD (FB-PSD), and two types of inter-electrode connectivity (IEC), band-based connectivity (BBC) and frequency-based connectivity (FBC), derived from resting-state EEG were subjected to feature selection with a proposed prior-compared minimum-redundancy maximum-relevance (PCMRMR) protocol. Their effectiveness was then tested by the supervised classification tasks using support vector machine (SVM), k-nearest neighbor (kNN), random forest (RF), and Gaussian classifier (GC). Brain networks of four somatosensory types were revealed by decoding fused multimodal data, namely type-averaged connectivity. The data from sixty healthy individuals were divided into training (n =59) and validation (n =1) datasets according to leave-one-subject-out (LOSO) criteria. The FBC was identified, which can serve as better brain signatures than BB-PSD, FB-PSD, and BBC to classify subjects as HS, NS, TS, or MS groups. Using the SVM, kNN, RF, and GC models, the best accuracy of 87% was obtained when classifying participants into HS, NS, TS, or MS groups. Moreover, the brain networks were decoded from HS, NS, TS, and MS groups by decoding the type-averaged connectivity fused from somatosensory phenotypes and selected FBC. It indicated that quantified multi-parameter somatosensory sensitivity could be achieved with acceptable accuracy, leading to considerable possibilities for using objective pain perception evaluation in clinical practice.

Relationship of dietary natural folate and synthetic folic acid co-exposure patterns with biological aging: findings from NHANES 2003-2018.

Background: The mandatory folic acid fortification program in the United States has inevitably exposed most Americans to both natural folate and synthetic folic acid. We aim to examine the association of dietary folate co-exposure patterns with biological aging indicators. Methods: A total of 18 889 participants were enrolled from 2003 to 2018. Dietary intake of folate from diverse sources was evaluated by 24-hour dietary recall. Biological aging indicators were developed based on age-related clinical indicators, including the phenotypic age (PA), Klemera-Doubal method (KDM), homeostatic dysregulation (HD), and allostatic load (AL). The unsupervised K-means clustering method, logistic regression model, and restricted cubic spline (RCS) regression model were used to explore the relationship of natural folate and synthetic folic acid co-exposure with biological aging indicators. Results: The results indicated that higher intake of total folate, dietary folate, and food natural folate was associated with lower PA [OR = 0.75 (0.64, 0.88); OR = 0.79 (0.70, 0.90); OR = 0.65 (0.57, 0.75)], KDM [OR = 0.63 (0.53, 0.75); OR = 0.80 (0.65, 0.98); OR = 0.62 (0.49, 0.77)], HD [OR = 0.69 (0.56, 0.84); OR = 0.78 (0.67, 0.92); OR = 0.78 (0.68, 0.90)], and AL [OR = 0.69 (0.58, 0.82); OR = 0.73 (0.63, 0.85); OR = 0.74 (0.62, 0.90)], consistently. Four co-exposure patterns were generated based on the intake of folate from diverse sources, as follows: "low folate exposure group" to cluster 1, "dietary folate exposure group" to cluster 2, "mixed source high folate exposure group" to cluster 3, and "mixed source excessive folate exposure group" to cluster 4. Compared with cluster 1, participants in cluster 2 are associated with lower biological age indicators (ORPA = 0.82 [0.72, 0.93]; ORKDM = 0.58 [0.47, 0.70]; ORHD = 0.85 [0.75, 0.97]; ORAL = 0.87 [0.77, 0.98]), while participants in cluster 3 and cluster 4 are not. Conclusion: For individuals subjected to folic acid fortification programs, a higher intake of dietary folate, especially natural folate, coupled with a lower consumption of folic acid supplements, was found to be associated with lower biological age indicators.

Identifying high-risk Fontan phenotypes using K-means clustering of cardiac magnetic resonance-based dyssynchrony metrics

BackgroundIndividuals with a Fontan circulation encompass a heterogeneous group with adverse outcomes linked to ventricular dilation, dysfunction, and dyssynchrony. The purpose of this study was to assess if unsupervised machine learning cluster analysis of cardiovascular magnetic resonance (CMR)-derived dyssynchrony metrics can separate ventricles in the Fontan circulation from normal control left ventricles and identify prognostically distinct subgroups within the Fontan cohort. MethodsThis single-center, retrospective study used 503 CMR studies from Fontan patients (median age 15 y) and 42 from age-matched controls from January 2005 to May 2011. Feature tracking on short-axis cine stacks assessed radial and circumferential strain, strain rate, and displacement. Unsupervised K-means clustering was applied to 24 mechanical dyssynchrony metrics derived from these deformation measurements. Clusters were compared for demographic, anatomical, and composite outcomes of death, or heart transplantation. ResultsFour distinct phenotypic clusters were identified. Over a median follow-up of 4.2 y (interquartile ranges 1.7–8.8 y), 58 (11.5%) patients met the composite outcome. The highest-risk cluster (largely comprised of right or mixed ventricular morphology and dilated, dyssynchronous ventricles) exhibited a higher hazard for the composite outcome compared to the lowest-risk cluster while controlling for ventricular morphology (hazard ratio [HR] 6.4; 95% confidence interval [CI] 2.1–19.3; P value 0.001) and higher indexed end-diastolic volume (HR 3.2; 95% CI 1.04–10.0; P value 0.043) per 10 mL/m2. ConclusionUnsupervised machine learning using CMR-derived dyssynchrony metrics identified four distinct clusters of patients with Fontan circulation and healthy controls with varying clinical characteristics and risk profiles. This technique can be used to guide future studies and identify more homogeneous subsets of patients from an overall heterogeneous population.

AET Volume 2 Nomor 3] Environmental, medical, and educational research sustainability in the age of technology: An editorial review

The six articles on Applied Engineering and Technology Volume 2 No 3 December 2023 presented have significant relevance in current engineering and technological developments to the three sectors: Environmental sustainability, Medicine, and Education. First, in an era that increasingly pays attention to environmental sustainability, as reflected in efforts to mitigate the environmental impact of the oil and gas industry, Effiom's research on developing bio-based drilling fluid becomes relevant and reflects the industry's efforts to adopt environmentally friendly solutions in the oil and gas exploration process [1]. This research develops and optimizes local pear seed-based biocyte fluid. Throughout the world, oil exploration and exploitation have had severe environmental impacts. So, it is very important to develop drilling fluid for oil exploration. This research optimizes drilling fluids by using biodegradable materials. The optimized drilling fluid contains environmentally friendly and cost-effective characteristics and is expected to be widely used in oil exploration, reducing adverse environmental impacts. Princewill et al. [2] conducted a safety and economic evaluation of boil-off gas (BOG) in global petroleum (LPG) storage tanks. BOG production impacts safety and economic profitability in the liquefied petroleum gas supply chain. This research evaluates BOG production due to heat leaks in storage tanks by analyzing thermodynamic properties and heat transfer equations. The research results show that maintaining isolation and external factors minimizes BOG formation. Therefore, this research provides essential guidance and suggestions for the safety and economic benefits of the liquefied petroleum gas supply chain. Finally, Yudanto et al. [3] used computational fluid dynamics (CFD) and Taguchi methods to calculate the CPU cooling system. The performance and stability of electronic devices are significant for users in today's rapid development of information technology. This study analyzes the impact of different cooling system configurations on CPU temperatures and provides practical insights into electronic thermite design. Through numerical simulations, the research results provide an essential reference for developing computer hardware design. Second, Agughasi and Srinivasiah [4] developed a semisupervised method for characterizing multiple chest X-ray images in the medical field. Accurate marker images are critical for training supervised learning models in medical image handling. However, manually tagging a large number of images requires time and effort. Therefore, this study suggests using unsupervised cluster technology-based K-Means and Self-Organizing Maps to produce reliable images. In this way, medical imaging processing costs can be reduced significantly, speeding up the research and application process. Meanwhile, in the education sector, Mariscal et al. [5] developed the mobile application MobILcaps to improve information literacy for social science students in higher education as a relevant instrument to facilitate teaching. Information literacy is crucial for developing individuals and society in today's information era. Based on cognitive, constructivist, and connectivity theories, this application has provided multimedia resources for students to facilitate independent learning. By working with teachers and students, this application provides practical tools and avenues for increasing students' information literacy levels. In addition, Riva et al. [6] developed AdPisika as an electronic learning system tailored to improve student academic achievement. In today's educational environment, personalized learning is critical to increasing the impact of learning for students. This research, based on learning style models and machine learning algorithms, personally optimizes learning materials, thereby improving students' learning performance. This system has significantly improved students' academic performance through experimental verification, providing practical ways to align education. In conclusion, these studies make essential contributions and provide valuable references and guidance for applying engineering and technology research and practice in the fields of Environmental sustainability, Medicine, and Education. Future research could investigate the depth and breadth of these areas and test the feasibility and effectiveness of such research through practical applications and experimental testing. In the context of environmental sustainability potential research includes exploration in the development of bio-based drilling fluid using alternative materials that are more environmentally friendly, research on green technology to reduce the impact of boil-off gas (BOG) in the LPG industry, and research on processor types and system configurations as well as the development of more efficient materials and more innovative cooling technology to improve the performance of the CPU cooling system. In the medical field, deepen semi-supervised labeling methods for medical image processing can focus on developing more sophisticated algorithms and further validation of various medical datasets. Meanwhile, in the educational context, developing broader mobile applications could increase information literacy. It could be useful if it adapted to various disciplines and research on integrating more advanced AI technology for adaptive e-learning systems more effectively.

Blood Monocyte Phenotype Is A Marker of Cardiovascular Risk in Type 2 Diabetes.

Diabetes is a major risk factor for atherosclerotic cardiovascular diseases with a 2-fold higher risk of cardiovascular events in people with diabetes compared with those without. Circulating monocytes are inflammatory effector cells involved in both type 2 diabetes (T2D) and atherogenesis. We investigated the relationship between circulating monocytes and cardiovascular risk progression in people with T2D, using phenotypic, transcriptomic, and metabolomic analyses. cardiovascular risk progression was estimated with coronary artery calcium score in a cohort of 672 people with T2D. Coronary artery calcium score was positively correlated with blood monocyte count and frequency of the classical monocyte subtype. Unsupervised k-means clustering based on monocyte subtype profiles revealed 3 main endotypes of people with T2D at varying risk of cardiovascular events. These observations were confirmed in a validation cohort of 279 T2D participants. The predictive association between monocyte count and major adverse cardiovascular events was validated through an independent prospective cohort of 757 patients with T2D. Integration of monocyte transcriptome analyses and plasma metabolomes showed a disruption of mitochondrial pathways (tricarboxylic acid cycle, oxidative phosphorylation pathway) that underlined a proatherogenic phenotype. In this study, we provide evidence that frequency and monocyte phenotypic profile are closely linked to cardiovascular risk in patients with T2D. The assessment of monocyte frequency and count is a valuable predictive marker for risk of cardiovascular events in patients with T2D. URL: https://www.clinicaltrials.gov; Unique identifier: NCT04353869.

IMAGE FEATURE EXTRACTION METHODS FOR STRUCTURE DETECTION FROM UNDERWATER IMAGERY

Abstract. The use of autonomous underwater vehicles (AUVs) for surveying underwater infrastructure presents a potential cost saving in comparison to remotely operated vehicles (ROVs). One of the challenges when processing images of underwater structures captured by an AUV, is that vast number of images captured during the mission usually do not show the structure. For instance, images captured during the dive to the structure or of the sea floor, or of the deep sea facing away from the structure. Too many images captured, without relevant information for a 3D reconstruction of the structure, leads to increased processing time and issues during the reconstruction process. There are two solutions to reduce the images to only images showing the structure. Firstly, only images of the structure are captured in the first place or remove images that are not useful after the capture and before further processing. This study developed and evaluated techniques that would enable the first strategy to be applied in an AUV. To apply this strategy in an AUV, would require an on-board structure detection system to ensure that they are correctly orientated for capturing useful footage during a survey mission. However, the marine environment poses several challenges to image-based object detection. Furthermore, small AUVs have limited power and computational resources available while deployed on a mission. To investigate the suitability of creating a lightweight structure detection model for the purpose of image evaluation, three computationally efficient image feature extraction methods (colour moments, local binary patterns (LBP), and Haar wavelet decomposition) were evaluated for their ability to distinguish underwater structures from background areas using unsupervised k-means models. LBP was found to be an effective method for identifying underwater structures in open water conditions. For identifying a structure against the seabed, colour moments were identified as the most effective method.

Objective characterisation of reinforced concrete with progressive corrosion defects through clustering and thresholding of infrared images

The research in this paper focuses on detection and quantification of subsurface damage in reinforced concrete (RC) structures by the analysis of infrared images. Experimental investigations were performed on RC slabs with embedded reinforcing bars (rebars). The corrosion mechanism in rebars was accelerated using an electrical circuit setup. The initial temperature of the slabs was adjusted in the environmental chamber and IR images were taken at regular intervals while they were exchanging heat to laboratory air through convection. Records of IR images were post-processed using an objective thresholding method proposed based on unsupervised k-means clustering. The results were discussed in context and with respect to the ASTM D 4788–03 recommendation for minimum detectable thermal contrast (0.5 °C) from delamination in bridge concrete by infrared thermography (IRT). The conclusions lead to recommendations for improved practical implementation of IRT that contribute to the broader prospects of structural health monitoring (SHM).

An open set model for pest identification

Agricultural pest identification is a prerequisite for increasing crop production and meeting global food demands. Generally, numerous phenotypic and genotypic features are widely utilized for species-level pest identification. However, the approaches are time-consuming and require expert knowledge in relevant fields. Numerous image-based machine learning (ML) models also exist to identify insect pests in agricultural fields. The models are significantly rely on a large, manually curated dataset and are close-set in nature. Our study aims to develop an open set pest identification approach by adding the capability of rejecting any irrelevant inputs. Tephritid fruit flies (Diptera:Tephritidae) are considered as an example since they are the most economically important agricultural pests worldwide. Images of the fruit flies were collected from a publicly available database and filtered to exclude uninformative images using a deep learning model (Inception-V3) and an unsupervised k-means clustering method. For the closed-set identification task, our EfficientNet-B2 model classified four major genera of notorious tephritid flies, namely, Anastrepha, Ceratitis, Rhagoletis, and Bactrocera with an accuracy of 89.65%. We further improvise our proposed model for open-set recognition tasks to leverage the identification beyond the trained datasets. The open set model achieved an overall accuracy of 86.48% and a macro F1-score of 94.44% on the four genera and an unknown class. Our proposed model can be a practical and effective pest identification tool for harmful fruit flies. In addition, the model is easy to implement with existing agricultural pest control systems in an open-world scenario.

Seismic attribute analysis with a combination of convolutional autoencoder and random forest in a turbidite reservoir

Due to the complex depositional environment of a turbidite reservoir in the Niuzhuang Delta, China, the traditional seismic facies classification is a challenge to perform accurately and continuously. Due to the thin turbidite layers in the reservoir, machine-learning-based prediction of sandstone thickness is challenging. Inspired by the autoencoder, we develop an open-source deep-learning workflow that combines unsupervised and supervised learning with jointed latent eigenvalues of the convolutional autoencoder (CAE) and traditional seismic attributes for seismic facies classification and sandstone thickness prediction constrained by the facies distribution. First, we extract lower-dimensional latent eigenvalues as a category of novel seismic attributes from the seismic data using a CAE. To accurately and effectively extract lower-dimensional latent eigenvalues, we develop a hybrid loss function based on the mean-squared error loss and the smooth L1 loss in this CAE. Then, we use principal component (PC) analysis to extract the first four PCs of these seismic lower-dimensional latent eigenvalues. Using unsupervised K-means, we cluster the first four PCs to form seismic facies. Finally, we take the first four PCs with the traditional seismic attributes as input and the sandstone thickness as labels for the random forest to predict the sandstone thickness distribution. The results of seismic facies and sandstone thickness distribution confirm the potential and advantages of our workflow, which can speed up the identification of seismic facies with smoother boundaries, improve the prediction accuracy by 16% over than that of traditional seismic attributes, and provide more depositional insight for a turbidite reservoir of the Shahejie Formation in the Niuzhuang Delta, China.