Search

Background: Catheter-related bladder discomfort (CRBD) commonly occurs in patients who have indwelling urinary catheters while under general anesthesia. And moderate-to-severe CRBD can lead to significant adverse events and negatively impact patient health outcomes. However, current screening studies for patients experiencing moderate-to-severe CRBD after waking from general anesthesia are insufficient. Constructing predictive models with higher accuracy using multiple machine learning techniques for early identification of patients at risk of experiencing moderate-to-severe CRBD during general anesthesia resuscitation., Methods: Eight hundred forty-six patients with indwelling urinary catheters who were resuscitated in a post-anesthesia care unit (PACU). Trained researchers used the CRBD 4-level assessment method to evaluate the severity of a patient's CRBD. They then inputted 24 predictors into six different machine learning algorithms. The performance of the models was evaluated using metrics like the area under the curve (AUC)., Results: The AUCs of the six models ranged from 0.82 to 0.89. Among them, the RF model displayed the highest predictive ability, with an AUC of 0.89 (95%CI: 0.87, 0.91). Additionally, it achieved an accuracy of 0.93 (95%CI: 0.91, 0.95), 0.80 sensitivity, 0.98 specificity, 0.94 positive predictive value (PPV), 0.92 negative predictive value (NPV), 0.87 F1 score, and 0.07 Brier score. The logistic regression (LR) model has achieved good results (AUC:0.87) and converted into a nomogram., Conclusions: The study has successfully developed a machine learning prediction model that exhibits excellent predictive capabilities in identifying patients who may develop moderate-to-severe CRBD after undergoing general anesthesia. Furthermore, the study also presents a nomogram, which serves as a valuable tool for clinical healthcare professionals, enabling them to intervene at an early stage for better patient outcomes., (© 2024. The Author(s).)

Background: Colorectal cancer significantly impacts global health, with unplanned reoperations post-surgery being key determinants of patient outcomes. Existing predictive models for these reoperations lack precision in integrating complex clinical data., Aim: To develop and validate a machine learning model for predicting unplanned reoperation risk in colorectal cancer patients., Methods: Data of patients treated for colorectal cancer ( n = 2044) at the First Affiliated Hospital of Wenzhou Medical University and Wenzhou Central Hospital from March 2020 to March 2022 were retrospectively collected. Patients were divided into an experimental group ( n = 60) and a control group ( n = 1984) according to unplanned reoperation occurrence. Patients were also divided into a training group and a validation group (7:3 ratio). We used three different machine learning methods to screen characteristic variables. A nomogram was created based on multifactor logistic regression, and the model performance was assessed using receiver operating characteristic curve, calibration curve, Hosmer-Lemeshow test, and decision curve analysis. The risk scores of the two groups were calculated and compared to validate the model., Results: More patients in the experimental group were ≥ 60 years old, male, and had a history of hypertension, laparotomy, and hypoproteinemia, compared to the control group. Multiple logistic regression analysis confirmed the following as independent risk factors for unplanned reoperation ( P < 0.05): Prognostic Nutritional Index value, history of laparotomy, hypertension, or stroke, hypoproteinemia, age, tumor-node-metastasis staging, surgical time, gender, and American Society of Anesthesiologists classification. Receiver operating characteristic curve analysis showed that the model had good discrimination and clinical utility., Conclusion: This study used a machine learning approach to build a model that accurately predicts the risk of postoperative unplanned reoperation in patients with colorectal cancer, which can improve treatment decisions and prognosis., Competing Interests: Conflict-of-interest statement: All authors declare that there is no conflict of interest involved in this study., (©The Author(s) 2024. Published by Baishideng Publishing Group Inc. All rights reserved.)

RNA pseudouridine modification is particularly important in a variety of cellular biological and physiological processes. It plays a significant role in understanding RNA functions, RNA structure stabilization, translation processes, etc. To understand its functional mechanisms, it is necessary to accurately identify pseudouridine sites in RNA sequences. Although some computational methods have been proposed for the identification of pseudouridine sites, it is still a challenge to improve the identification accuracy and generalization ability. To address this challenge, a novel feature fusion predictor, named PsoEL-PseU, is proposed for the prediction of pseudouridine sites. Firstly, this study systematically and comprehensively explored different types of feature descriptors and determined six feature descriptors with various properties. To improve the feature representation ability, a binary particle swarm optimizer was used to capture the optimal feature subset for six feature descriptors. Secondly, six individual predictors were trained by using the six optimal feature subsets. Finally, to fuse the effects of all six features, six individual predictors were fused into an ensemble predictor by a parallel fusion strategy. Ten-fold cross-validation on three benchmark datasets indicated that the PsoEL-PseU predictor significantly outperformed the current state-of-the-art predictors. Additionally, the new predictor achieved better accuracy in the independent dataset evaluation-accuracy which is significantly higher than that of its existing counterparts-and the user-friendly webserver developed by the PsoEL-PseU predictor has been made freely accessible.

This paper studies a novel robotic warehousing system called the overhead robotic compact storage and retrieval system, which can free up the floor space occupation at a low cost. Bins, as basic storage containers, are stacked on top of each other to form a bin stack. Along overhead tracks, bin-picking robots transport bins between storage/retrieval positions and workstations with the aid of track-changing robots. Little research has been done to study operational policies and performance analysis for this new robotic compact warehousing system. We propose a nested queuing network model that considers two transportation resources and performs reinforcement learning using real data to improve the reshuffling efficiency. We find that reinforcement learning based reshuffling policy greatly reduces the reshuffling distance and saves computation time compared to existing policies. We find that the storage policy of stacks affects the optimal width/length ratio regardless of the system height. Interestingly, we obtain the number of robots that can stabilise the system to avoid an explosion of the order queue; two more robots than that number will produce relatively low throughput times. Compared to an AutoStore system, using our system reduces cost by 30% with a slight increase in throughput time. [ABSTRACT FROM AUTHOR]

In thrombotic diseases, coagulation, anticoagulation, and fibrinolysis are three key physiological processes that interact to maintain blood in an appropriate state within blood vessels. When these processes become imbalanced, such as excessive coagulation or reduced anticoagulant function, it can lead to the formation of blood clots. Genetic factors play a significant role in the onset of thrombotic diseases and exhibit regional and ethnic variations. The decision of whether to initiate prophylactic anticoagulant therapy is a matter that clinicians must carefully consider, leading to the development of various thrombotic risk assessment scales in clinical practice. Given the considerable heterogeneity in clinical diagnosis and treatment, researchers are exploring the application of artificial intelligence in medicine, including disease prediction, diagnosis, treatment, prevention, and patient management. This paper reviews the research progress on various genetic factors involved in thrombotic diseases, analyzes the advantages and disadvantages of commonly used thrombotic risk assessment scales and the characteristics of ideal scoring scales, and explores the application of artificial intelligence in the medical field, along with its future prospects. [ABSTRACT FROM AUTHOR]

Thanks to the introduction of non‐fullerene acceptors, efficiencies of organic photovoltaics are now approaching 20%. Closing the gap with inorganic photovoltaics requires minimizing voltage losses without penalizing charge extraction, for which microstructure control is crucial. However, the complex interplay between microstructure and charge generation, recombination, and extraction has so far not been unraveled. Here, a systematic study linking device performance to distinct microstructural features via machine learning is presented. Building bi‐layer devices allows to separately study the influence of aggregation and disorder on the energies and lifetimes of bulk and interfacial states. Unambiguous assignments of specific structural motifs to the device photophysics are thus possible. It is found that the control of aggregation‐caused quenching is decisive for the exciton splitting efficiency and thus the carrier generation. Furthermore, the static disorder at the donor–acceptor interface controls the nonradiative recombination by shifting the excited state population from the bulk toward the interface. Finally, the amount of disorder in the bulk is found decisive for charge extraction. The finding that charge generation, recombination, and extraction are controlled by distinct structural features, is the key to optimizing these motifs independently, which will pave the way for organic photovoltaics toward the detailed balance limit. [ABSTRACT FROM AUTHOR]

To ensure the safety and durability of concrete structures, timely detection and classification of concrete cracks using a low-cost and high-efficiency method is necessary. In this study, a concrete surface crack damage detection method based on the ResNet-18 residual network was developed. This method was implemented by training a model with images to extract the cracks, where the image processing algorithms and deep learning were combined. The results show that the computational accuracy can meet the requirements by utilizing the established image dataset and appropriate model hyperparameters. The trained model had high recognition accuracy when the 256 × 256 resolution images were adopted, and the worst accuracy of crack recognition in the test set was over 90%. The average accuracy in the test set was 91.3% when considering environmental interference generated by processing the images with a brightness adjustment, salt-and-pepper noise, and localized interference. Then, it was demonstrated that the present model possesses good robustness for crack identification in different environments. The average recognition accuracy when dealing with images of a real bridge, which are outside the training dataset, was 99.7%. The residual network model developed in this study has the advantages of low cost, high efficiency, and practicality compared to traditional detection methods. Compared to the existing deep learning methods, the model created in this study requires less computational resources and storage space, and shows a faster training speed and higher accuracy. [ABSTRACT FROM AUTHOR]

Simple Summary: RNA pseudouridine modifications are present in various RNAs across different organisms and play crucial roles in regulating gene expression during biological processes. The accurate identification of pseudouridine sites within RNA sequences is essential for understanding their functional mechanisms. This study proposes a novel ensemble learning predictor named PseUpred-ELPSO, which accurately predicts RNA pseudouridine sites. The predictor demonstrates excellent performance in both cross-validation and independent testing. A user-friendly web server has been established, making it a powerful tool for pseudouridine site identification. RNA pseudouridine modification exists in different RNA types of many species, and it has a significant role in regulating the expression of biological processes. To understand the functional mechanisms for RNA pseudouridine sites, the accurate identification of pseudouridine sites in RNA sequences is essential. Although several fast and inexpensive computational methods have been proposed, the challenge of improving recognition accuracy and generalization still exists. This study proposed a novel ensemble predictor called PseUpred-ELPSO for improved RNA pseudouridine site prediction. After analyzing the nucleotide composition preferences between RNA pseudouridine site sequences, two feature representations were determined and fed into the stacking ensemble framework. Then, using five tree-based machine learning classifiers as base classifiers, 30-dimensional RNA profiles are constructed to represent RNA sequences, and using the PSO algorithm, the weights of the RNA profiles were searched to further enhance the representation. A logistic regression classifier was used as a meta-classifier to complete the final predictions. Compared to the most advanced predictors, the performance of PseUpred-ELPSO is superior in both cross-validation and the independent test. Based on the PseUpred-ELPSO predictor, a free and easy-to-operate web server has been established, which will be a powerful tool for pseudouridine site identification. [ABSTRACT FROM AUTHOR]

Antimicrobial peptides (AMPs) are vital components of innate immunotherapy. Existing approaches mainly rely on either deep learning for the automatic extraction of sequence features or traditional manual amino acid features combined with machine learning. The peptide sequence contains symmetrical sequence motifs or repetitive amino acid patterns, which may be related to the function and structure of the peptide. Recently, the advent of large language models has significantly boosted the representational power of sequence pattern features. In light of this, we present a novel AMP predictor called UniproLcad, which integrates three prominent protein language models—ESM-2, ProtBert, and UniRep—to obtain a more comprehensive representation of protein features. UniproLcad utilizes deep learning networks, encompassing the bidirectional long and short memory network (Bi-LSTM) and one-dimensional convolutional neural networks (1D-CNN), while also integrating an attention mechanism to enhance its capabilities. These deep learning frameworks, coupled with pre-trained language models, efficiently extract multi-view features from antimicrobial peptide sequences and assign attention weights to them. Through ten-fold cross-validation and independent testing, UniproLcad demonstrates competitive performance in the field of antimicrobial peptide identification. This integration of diverse language models and deep learning architectures enhances the accuracy and reliability of predicting antimicrobial peptides, contributing to the advancement of computational methods in this field. [ABSTRACT FROM AUTHOR]

Inductive Logic Programming (ILP) is a research field at the intersection between machine learning and logic programming, focusing on developing a formal framework for inductively learning relational descriptions in the form of logic programs from examples and background knowledge. As an emerging method of ILP, Meta-Interpretive Learning (MIL) leverages the specialization of a set of higher-order metarules to learn logic programs. In MIL, the input includes a set of examples, background knowledge, and a set of metarules, while the output is a logic program. MIL executes a depth-first traversal search, where its program search space expands polynomially with the number of predicates in the provided background knowledge and exponentially with the number of clauses in the program, sometimes even leading to search collapse. To address this challenge, this study introduces a strategy that employs the concept of reuse, specifically through the integration of auxiliary predicates, to reduce the number of clauses in programs and improve the learning efficiency. This approach focuses on the proactive identification and reuse of common program patterns. To operationalize this strategy, we introduce MILER, a novel method integrating a predicate generator, program learner, and program evaluator. MILER leverages frequent subgraph mining techniques to detect common patterns from a limited dataset of training samples, subsequently embedding these patterns as auxiliary predicates into the background knowledge. In our experiments involving two Visual Question Answering (VQA) tasks and one program synthesis task, we assessed MILER's approach to utilizing reusable program patterns as auxiliary predicates. The results indicate that, by incorporating these patterns, MILER identifies reusable program patterns, reduces program clauses, and directly decreases the likelihood of timeouts compared to traditional MIL. This leads to improved learning success rates by optimizing computational efforts. [ABSTRACT FROM AUTHOR]

Background: Radiomics is increasingly utilized to distinguish pulmonary nodules between lung adenocarcinoma (LUAD) and tuberculosis (TB). However, it remains unclear whether different segmentation criteria, such as the inclusion or exclusion of the cavity region within nodules, affect the results. Methods: A total of 525 patients from two medical centers were retrospectively enrolled. The radiomics features were extracted according to two regions of interest (ROI) segmentation criteria. Multiple logistic regression models were trained to predict the pathology: (1) The clinical model relied on clinical‐radiological semantic features; (2) The radiomics models (radiomics+ and radiomics−) utilized radiomics features from different ROIs (including or excluding cavities); (3) the composite models (composite+ and composite−) incorporated both above. Results: In the testing set, the radiomics+/− models and the composite+/− models still possessed efficient prediction performance (AUC ≥ 0.94), while the AUC of the clinical model was 0.881. In the validation set, the AUC of the clinical model was only 0.717, while that of the radiomics+/− models and the composite+/− models ranged from 0.801 to 0.825. The prediction performance of all the radiomics+/− and composite+/− models were significantly superior to that of the clinical model (p < 0.05). Whether the ROI segmentation included or excluded the cavity had no significant effect on these models (radiomics+ vs. radiomics−, composite+ model vs. composite−) (p > 0.05). Conclusions: The present study established a machine learning‐based radiomics strategy for differentiating LUAD from TB lesions. The ROI segmentation including or excluding the cavity region may exert no significant effect on the predictive ability. [ABSTRACT FROM AUTHOR]

Objective: The objective of this study was to discover differential metabolites and pathways underlying infrequent gout flares (InGF) and frequent gout flares (FrGF) using metabolomics and to establish a predictive model by machine learning (ML) algorithms. Methods: Serum samples from a discovery cohort of 163 patients with InGF and 239 patients with FrGF were analyzed by mass spectrometry–based untargeted metabolomics to profile differential metabolites and explore dysregulated metabolic pathways using pathway enrichment analysis and network propagation–based algorithms. ML algorithms were performed to establish a predictive model based on selected metabolites, which was further optimized by a quantitative targeted metabolomics method and validated in an independent validation cohort with 97 participants with InGF and 139 participants with FrGF. Results: A total of 439 differential metabolites between InGF and FrGF groups were identified. Top dysregulated pathways included carbohydrates, amino acids, bile acids, and nucleotide metabolism. Subnetworks with maximum disturbances in the global metabolic networks featured cross‐talk between purine metabolism and caffeine metabolism, as well as interactions among pathways involving primary bile acid biosynthesis, taurine and hypotaurine metabolism, alanine, aspartate, and glutamate metabolism, suggesting epigenetic modifications and gut microbiome in metabolic alterations underlying InGF and FrGF. Potential metabolite biomarkers were identified using ML‐based multivariable selection and further validated by targeted metabolomics. Area under receiver operating characteristics curve for differentiating InGF and FrGF achieved 0.88 and 0.67 for the discovery and validation cohorts, respectively. Conclusion: Systematic metabolic alterations underlie InGF and FrGF, and distinct profiles are associated with differences in gout flare frequencies. Predictive modeling based on selected metabolites from metabolomics can differentiate InGF and FrGF. [ABSTRACT FROM AUTHOR]

Aiming at the problem of fast divergence of pure inertial navigation system without correction under the condition of GNSS restricted environment, this paper proposes a multi-mode navigation method with an intelligent virtual sensor based on long short-term memory (LSTM). The training mode, predicting mode, and validation mode for the intelligent virtual sensor are designed. The modes are switching flexibly according to GNSS rejecting situation and the status of the LSTM network of the intelligent virtual sensor. Then the inertial navigation system (INS) is corrected, and the availability of the LSTM network is also maintained. Meanwhile, the fireworks algorithm is adopted to optimize the learning rate and the number of hidden layers of LSTM hyperparameters to improve the estimation performance. The simulation results show that the proposed method can maintain the prediction accuracy of the intelligent virtual sensor online and shorten the training time according to the performance requirements adaptively. Under small sample conditions, the training efficiency and availability ratio of the proposed intelligent virtual sensor are improved significantly more than the neural network (BP) as well as the conventional LSTM network, improving the navigation performance in GNSS restricted environment effectively and efficiently. [ABSTRACT FROM AUTHOR]

As machine vision technology has advanced, pig face recognition has gained wide attention as an individual pig identification method. This study establishes an improved ResNAM network as a backbone network for pig face image feature extraction by combining an NAM (normalization-based attention module) attention mechanism and a ResNet model to probe non-contact open-set pig face recognition. Then, an open-set pig face recognition framework is designed by integrating three loss functions and two metrics to finish the task with no crossover of individuals in the training and test sets. The SphereFace loss function with the cosine distance as a metric and ResNAM are combined in the framework to obtain the optimal open-set pig face recognition model. To train our model, 37 pigs with a total of 12,993 images were randomly selected from the collected pig face images, and 9 pigs with a total of 3431 images were set as a test set. 900 pairs of positive sample pairs and 900 pairs of negative pairs were obtained from the images in the test set. A series of experimental results show that our accuracy reached 95.28%, which was 2.61% higher than that of a human face recognition model. NAM was more effective in improving the performance of the pig face recognition model than the mainstream BAM (bottleneck attention module) and CBAM (convolutional block attention module). The research results can provide technological support for non-contact open-set individual recognition for intelligent farming processes. [ABSTRACT FROM AUTHOR]

Linear discriminant analysis (LDA) has been proven to be effective in dimensionality reduction. However, the performance of LDA depends on the consistency assumption of the global structure and the local structure. Some work extended LDA along this line of research and proposed local formulations of LDA. Unfortunately, the learning scheme of these algorithms is suboptimal in that the intrinsic relationship between data points is pre-learned in the original space, which is usually affected by the noise and redundant features. Besides, the time cost is relatively high. To alleviate these drawbacks, we propose a Fast Locality Discriminant Analysis framework (FLDA), which has three advantages: (1) It can divide a non-Gaussian distribution class into many sub-blocks that obey Gaussian distributions by using the anchor-based strategy. (2) It captures the manifold structure of data by learning the fuzzy membership relationship between data points and the corresponding anchor points, which can reduce computation time. (3) The weights between data points and anchor points are adaptively updated in the subspace where the irrelevant information and the noise in high-dimensional space have been effectively suppressed. Extensive experiments on toy data sets, UCI benchmark data sets and imbalanced data sets demonstrate the efficiency and effectiveness of the proposed method. [ABSTRACT FROM AUTHOR]

Hemorrhagic events are the main focus of attention during antithrombosis therapy in patients with coronary artery disease (CAD). This study aims to investigate the potential of using photoplethysmography (PPG) and machine learning techniques to assess hemorrhagic risk in patients with CAD. A total of 1638 patients with CAD were enrolled from January 2018 to October 2019, among which 114 patients were observed to have at least one positive event. Importantly, 102 patients with 9933 records were finally retained for analysis in this study. Participants were required to collect data using the portable PPG acquisition device and the specially designed Android APP. The data was collected and uploaded to a remote server. Based on collected PPG signals, we extracted features in a total of 30 dimensions from time-domain, frequency-domain, and wavelet packet decomposition. Logistic regression, support vector regression, random forest, and XGBoost regression models were established to achieve hemorrhagic risk evaluation, and then, their performances were compared. In total, 10 features extracted from PPG showed statistical significance (p < 0.01) between negative and positive groups. The newly established XGBoost model performed best in the hemorrhagic risk evaluation experiment, wherein the mean area under the curve (AUC) with tenfold cross-validation was 0.762 ± 0.024 and the sensitivity and specificity were 0.679 ± 0.051 and 0.714 ± 0.014, respectively. We established a data acquisition system for PPG signal collection, and demonstrated that a set of features extracted from PPG and the proposed machine learning model are promising in the evaluation of hemorrhagic risk among patients with CAD. In comparison with the traditional HAS-BLED score, the proposed method can obtain the quantitative risk prediction probability from a single PPG record, which has the advantages of dynamics and continuity, and can provide timely feedback for doctors' antithrombotic treatment, which is of great significance for doctors to quickly determine the effectiveness of the treatment and adjust the timely treatment plans accordingly. [ABSTRACT FROM AUTHOR]

Semi-supervised learning as one of most attractive problems in machine learning research field has aroused broad attentions in recent years. In this paper, we propose a novel locality preserved dimensionality reduction framework, named Semi-supervised Adaptive Local Embedding learning (SALE), which learns a local discriminative embedding by constructing a $k_1$ k 1 Nearest Neighbors ($k_1$ k 1 NN) graph on labeled data, so as to explore the intrinsic structure, i.e., sub-manifolds from non-Gaussian labeled data. Then, mapping all samples into learned embedding and constructing another $k_2$ k 2 NN graph on all embedded data to explore the global structure of all samples. Therefore, the unlabeled data and their corresponding labeled neighbors can be clustered into same sub-manifold, so as to improve the discriminative power of embedded data. Furthermore, we propose two semi-supervised dimensionality reduction methods with orthogonal and whitening constraints based on proposed SALE framework. An efficient alternatively iterative optimization algorithm is developed to solve the NP-hard problem in our models. Extensive experiments conducted on several synthetic and real-world data sets demonstrate the superiorities of our methods on local structure exploration and classification task. [ABSTRACT FROM AUTHOR]

Glioma is the most common primary malignant brain tumor in adults. It accounts for about 75% of such tumors and occurs more commonly in men. The incidence rate has been increasing in the past 30 years. Moreover, the 5-year overall survival rate of glioma patients is < 35%. Different locations, grades, and molecular characteristics of gliomas can lead to different behavioral deficits and prognosis, which are closely related to patients' quality of life and associated with neuroplasticity. Some advanced magnetic resonance imaging (MRI) technologies can explore the neuroplasticity of structural, topological, biochemical metabolism, and related mechanisms, which may contribute to the improvement of prognosis and function in glioma patients. In this review, we summarized the studies conducted on structural and topological plasticity of glioma patients through different MRI technologies and discussed future research directions. Previous studies have found that glioma itself and related functional impairments can lead to structural and topological plasticity using multimodal MRI. However, neuroplasticity caused by highly heterogeneous gliomas is not fully understood, and should be further explored through multimodal MRI. In addition, the individualized prediction of functional prognosis of glioma patients from the functional level based on machine learning (ML) is promising. These approaches and the introduction of ML can further shed light on the neuroplasticity and related mechanism of the brain, which will be helpful for management of glioma patients. [ABSTRACT FROM AUTHOR]

$k$ k -means method using Lloyd heuristic is a traditional clustering method which has played a key role in multiple downstream tasks of machine learning because of its simplicity. However, Lloyd heuristic always finds a bad local minimum, i.e., the bad local minimum makes objective function value not small enough, which limits the performance of $k$ k -means. In this paper, we use coordinate descent (CD) method to solve the problem. First, we show that the $k$ k -means minimization problem can be reformulated as a trace maximization problem, then a simple and efficient coordinate descent scheme is proposed to solve the maximization problem. Two interesting findings through theory are that Lloyd cannot decrease the objective function value of $k$ k -means produced by our CD further, and our proposed method CD to solve $k$ k -means problem can avoid produce empty clusters. In addition, according to the computational complexity analysis, it is verified CD has the same time complexity with original $k$ k -means method. Extensive experiments including statistical hypothesis testing, on several real-world datasets with varying number of clusters, varying number of samples and varying number of dimensions show that CD performs better compared to Lloyd, i.e., lower objective value, better local minimum and fewer iterations. And CD is more robust to initialization than Lloyd whether the initialization strategy is random or initialization of $k$ k -means++. [ABSTRACT FROM AUTHOR]

Feature selection is one of the most important techniques to deal with the high-dimensional data for a variety of machine learning and data mining tasks, such clustering, classification, and retrieval, etc. Fuzziness is a widespread nature of data in nature human society. However, most existing feature selection methods ignore the existence of fuzziness in the data, resulting in sub-optimal feature subsets. To address the problem, we propose a novel unsupervised feature selection method, called Unsupervised Discriminative Projection for Feature Selection (UDPFS) to select discriminative features by conducting fuzziness learning and sparse learning, simultaneously. Specifically, we use projection matrix transform data as its low-dimensional representation, which are partitioned into clusters by using membership matrix with sparse constraint. In addition, $\ell _{2, 1}$ ℓ 2 , 1 -norm regularization is applied to the projection matrix. Then, a discriminative projection matrix with row sparse is obtained by perform fuzziness learning and sparse learning, simultaneously. An effective alternative optimization algorithm is proposed to solve the objective function. Evaluate experimental results on several real-world datasets show the effectiveness and superiority of the proposed unsupervised feature selection method. [ABSTRACT FROM AUTHOR]

The use of neural machine algorithms for English translation is a hot topic in the current research. English translation using the traditional sequential neural framework, which is too poor at capturing long-distance information, has its own major limitations. However, the current improved frameworks, such as recurrent neural network translation, are not satisfactory either. In this paper, we establish an attention coding and decoding model to address the shortcomings of traditional machine translation algorithms, combine the attention mechanism with a neural network framework, and implement the whole English translation system based on TensorFlow, thus improving the translation accuracy. The experimental test results show that the BLUE values of the algorithm model built in this paper are improved to different degrees compared with the traditional machine learning algorithms, which proves that the performance of the proposed algorithm model is significantly improved compared with the traditional model. [ABSTRACT FROM AUTHOR]

The existing federated learning framework is based on the centralized model coordinator, which still faces serious security challenges such as device differentiated computing power, single point of failure, poor privacy, and lack of Byzantine fault tolerance. In this paper, we propose an asynchronous federated learning system based on permissioned blockchains, using permissioned blockchains as the federated learning server, which is composed of a main-blockchain and multiple sub-blockchains, with each sub-blockchain responsible for partial model parameter updates and the main-blockchain responsible for global model parameter updates. Based on this architecture, a federated learning asynchronous aggregation protocol based on permissioned blockchain is proposed that can effectively alleviate the synchronous federated learning algorithm by integrating the learned model into the blockchain and performing two-order aggregation calculations. Therefore, the overhead of synchronization problems and the reliability of shared data is also guaranteed. We conducted some simulation experiments and the experimental results showed that the proposed architecture could maintain good training performances when dealing with a small number of malicious nodes and differentiated data quality, which has good fault tolerance, and can be applied to edge computing scenarios. [ABSTRACT FROM AUTHOR]

PM 2.5 is the main component of most haze, and the presence of high concentrations of PM 2.5 in the air for an extended time can cause serious effects on human health, so there is an urgent need for research work related to PM 2.5. Traditional PM 2.5 monitoring uses ground-based monitoring stations with low spatial resolution. Other studies have retrieved the Moderate Resolution Imaging Spectroradiometer aerosol optical depth product by the dark-target algorithm. However, the estimated PM 2.5 concentration on the ground will produce missing values, which will lead to the reduction of spatial and temporal resolution. Based on this, this study proposes a machine learning algorithm to estimate PM 2.5 by using the fifth generation reanalysis (ERA5) data set published by the European Center for Medium-range Weather Forecasts (ECMWF). In this study, two different methods of back propagation neural network (BPNN) and random forest (RF) were used to develop the models. Firstly, the meteorological parameters (precipitable water vapor, water vapor pressure and relative humidity, etc.) and pollution parameters (O 3 , CO, NO 2 , SO 2 , PM 10 , and PM 2.5) were used to establish PM 2.5 model in 2021. The results showed that the R2 and RMSE for BPNN and RF were 0.94/0.96 and 10.37/8.77 µg/m3, respectively. Then, due to the lack and the low spatial resolution of the pollution parameters, using only the ERA5 meteorological data with the high spatiotemporal resolution to develop the PM 2.5 model in winter, the R2 of the RF model (0.93) was 0.05 higher and the RMSE (12.50 µg/m3) was 4.19 µg/m3 lower than that of the BPNN model, which indicates that it is feasible to develop the PM 2.5 model using only meteorological parameters. Finally, using the RF model of the second stage and ERA5 meteorological data with a spatial resolution of 0.05° (obtained by cubic spline interpolation) to generate the hourly PM 2.5 map of Beijing and compare it with China High Air Pollutants dataset, the R2 and RMSE of Beijing were 0.78 µg/m3 and 14.85 µg/m3, respectively. On this basis, it is found that the areas with high PM 2.5 concentration are close to the areas with serious pollution in Hebei Province by analyzing the PM 2.5 map of Beijing, and area transport and human activities are important sources of air pollution. [ABSTRACT FROM AUTHOR]

The Fourier transform infrared (FTIR) imaging technique was used in a transmission model for the evaluation of twelve oral hyperkeratosis (HK), eleven oral epithelial dysplasia (OED), and eleven oral squamous cell carcinoma (OSCC) biopsy samples in the fingerprint region of 1800–950 cm−1. A series of 100 µm × 100 µm FTIR imaging areas were defined in each sample section in reference to the hematoxylin and eosin staining image of an adjacent section of the same sample. After outlier removal, signal preprocessing, and cluster analysis, a representative spectrum was generated for only the epithelial tissue in each area. Two representative spectra were selected from each sample to reflect intra-sample heterogeneity, which resulted in a total of 68 representative spectra from 34 samples for further analysis. Exploratory analyses using Principal component analysis and hierarchical cluster analysis showed good separation between the HK and OSCC spectra and overlaps of OED spectra with either HK or OSCC spectra. Three machine learning discriminant models based on partial least squares discriminant analysis (PLSDA), support vector machines discriminant analysis (SVMDA), and extreme gradient boosting discriminant analysis (XGBDA) were trained using 46 representative spectra from 12 HK and 11 OSCC samples. The PLSDA model achieved 100% sensitivity and 100% specificity, while both SVM and XGBDA models generated 95% sensitivity and 96% specificity, respectively. The PLSDA discriminant model was further used to classify the 11 OED samples into HK-grade (6), OSCC-grade (4), or borderline case (1) based on their FTIR spectral similarity to either HK or OSCC cases, providing a potential risk stratification strategy for the precancerous OED samples. The results of the current study support the application of the FTIR-machine learning technique in early oral cancer detection. [ABSTRACT FROM AUTHOR]

Unsupervised feature selection is a hot topic in the field of machine learning, which is more convenient and important because it does not require labeled data. Currently, unsupervised feature selection algorithms based on ℓ 2 , 1 -norm are very mature and have certain robustness to outliers, but they still have some problems that cannot be ignored. For example, the sparsity of ℓ 2 , 1 -norm is not ideal, they cannot achieve row sparsity but only element sparsity. Second, fine-tuning meaningless regularization parameters increases cost and makes it easy to fall into suboptimal solutions. To release the above problems, we propose an unsupervised feature selection algorithm via Sparse Robust Subspace Learning (SRSL), which combines reconstruction term and variance term so that the model simultaneously preserves reconstruction information and enhances separability. What is more, using the ℓ 2 , 0 -norm constraint on transformation matrix makes our model have a row-sparse property. In addition, we design the boolean weight so that the model not only eliminates outliers fundamentally to enhance robustness, but also achieves the effect of anomaly detection. To solve this NP-hard problem, we carefully design an optimization algorithm, which has strict convergence guarantees and obtains a closed-form solution. Experimental results on several real-world datasets demonstrate that our algorithm outperforms other comparison algorithms in both clustering and anomaly detection applications. [Display omitted] • A robust feature selection method based on reconstruction and variance is proposed. • Designing boolean weight to fundamentally eliminate outliers. • Designing an algorithm to solve ℓ 2 , 0 -norm constrained problem of feature selection. • Our algorithm has significant advantages in practical applications. [ABSTRACT FROM AUTHOR]

With the rapid development of intelligent systems, such as self-driving vehicles, service robots and surveillance systems, pedestrian trajectory prediction has become a very challenging problem. How to perceive, understand and predict the motion patterns of pedestrians in a highly crowded and chaotic environment in order to prevent future collisions becomes a top priority. The motion of pedestrians is not only affected by their own factors, but also by surrounding neighbors. To solve the above problems, we propose a model named PTPGC based on graph attention and convolutional long short-term memory (ConvLSTM) network to predict multiple reasonable pedestrian trajectories. Firstly, the pedestrians are represented in a dynamic graph by setting a Euclidean distance threshold. Then, a graph attention network is used to learn the spatial interaction relationship of all pedestrians in each time step, and a temporal convolutional network (TCN) is used to encode the pedestrians' own factors. Finally, we use the ConvLSTM to iteratively predict the multiple reasonable and feasible future trajectories of pedestrians. Experiments show that our model has a higher prediction accuracy on two public pedestrian data sets (ETH and UCY) compared with the existing baselines for pedestrian trajectory prediction, and the generated trajectories are more in line with social rationality and physical constraints. • We use the TCN to extract all the information of pedestrians in the time dimension without forgetting any information. • We use graph attention to aggregate and update pedestrians' information in the space dimension. • By using ConvLSTM, we predict multiple reasonable trajectories conforming to physical rules and social norms. [ABSTRACT FROM AUTHOR]

• A novel nonlinear feature selective networks is designed. • Proposed method is applied for continuous values regression. • An optimizer joins back propagation and re-weighted is designed. The curse of dimensionality is a long-standing intractable issue in many machine learning and computer vision tasks. Feature selection, a data preprocessing technique, aims to select most discriminative feature subsets for improving performance of downstream machine learning tasks. However, most existing feature selection methods concentrate upon learning a linear relationship between data points and their labels, which causes that they are incapable of handling nonlinear complex data in real-world applications. In this paper, we first propose a novel end-to-end Nonlinear Feature Selective Networks (NFSN) that be able to select discriminative feature subsets while preserving their nonlinear structure by embedding a ℓ 2 , p -norm regularized hidden layer into designed continuous values regression networks. In addition, we propose an efficient optimization algorithm that joins back propagation algorithm and re-weighted optimization strategy to acquire derivative of all weights accurately. Experimental results on the nonlinear analog pulse signal and real-world datasets demonstrate the superiority of proposed method compared to some related methods on feature selection. Our source code available on: https://github.com/StevenWangNPU/NFSN. [ABSTRACT FROM AUTHOR]

Periodontitis is a chronic inflammation of the periodontium caused by a persistent bacterial infection, resulting in destruction of the supporting structures of teeth. Analysis of microbial composition in saliva can inform periodontal status. Actinobacillus actinomycetemcomitans (Aa), Porphyromonas gingivalis (Pg), and Streptococcus mutans (Sm) are among reported periodontal pathogens, and were used as model systems in this study. Our atomic force microscopic (AFM) study revealed that these pathogens are biological nanorods with dimensions of 0.6–1.1 μm in length and 500–700 nm in width. Current bacterial detection methods often involve complex preparation steps and require labeled reporting motifs. Employing surface-enhanced Raman spectroscopy (SERS), we revealed cell-type specific Raman signatures of these pathogens for label-free detection. It overcame the complexity associated with spectral overlaps among different bacterial species, relying on high signal-to-noise ratio (SNR) spectra carefully collected from pure species samples. To enable simple, rapid, and multiplexed detection, we harnessed advanced machine learning techniques to establish predictive models based on a large set of raw spectra of each bacterial species and their mixtures. Using these models, given a raw spectrum collected from a bacterial suspension, simultaneous identification of all three species in the test sample was achieved at 95.6 % accuracy. This sensing modality can be applied to multiplex detection of a broader range and a larger set of periodontal pathogens, paving the way for hassle-free detection of oral bacteria in saliva with little to no sample preparation. [ABSTRACT FROM AUTHOR]

Large-scale cluster extended reach wells (ERWs) are usually drilled from one platform to target distant multiple reservoirs in offshore oil & gas development. Due to the complicated downhole environments and complex geological conditions in various azimuths, the accurate prediction of the rate of penetration (ROP) in offshore large-scale cluster ERWs drilling is a challenging task. In this work, a ROP prediction method for offshore large-scale cluster ERWs drilling based on machine learning and big-data techniques is presented. 27 input parameters affecting ROP are collected from block N of China Bohai Oilfield, with a total of 9,193,408 data points. The internal relation between various parameters and ROP at the data level is revealed, which verifies the feasibility of the collected data set training. Based on various machine learning algorithms, 12 kinds of ROP prediction models based on support vector regression (SVR), random forest regression (RFR), back propagation neural network (BPNN), and recurrent neural network (RNN) are established respectively. Meanwhile, the prediction accuracy of the ROP prediction models is evaluated based on six performance indicators. It shows that the prediction results of the RNN model with LSTM as neuron structure are the best (all of the 6 indicators are optimal) among the 12 kinds of ROP prediction models, and the mean absolute error is only 6.12 m/h. The RNN model with LSTM as neuron structure is the best machine learning model in the prediction of ROP in offshore large-scale cluster ERWs drilling. It provides a practical method for enhancing cleaner development of offshore oil & gas. • A ROP prediction method for offshore large-scale cluster ERWs drilling is presented. • 12 kinds of ROP prediction models are established based on machine learning & big-data. • The prediction accuracy of the 12 kinds of ROP prediction models is evaluated. [ABSTRACT FROM AUTHOR]