► A nearest neighbor selection is proposed for iteratively kNN imputation of missing data, named GkNN (gray kNN) imputation. ► The GkNN utilizes all the imputed instances as observed data with ...complete instances (instances without missing values) together for consequent imputation iteration. ► The GkNN algorithm is extended for imputing heterogeneous datasets that are with both numerical and categorical attributes.
Existing kNN imputation methods for dealing with missing data are designed according to Minkowski distance or its variants, and have been shown to be generally efficient for numerical variables (features, or attributes). To deal with heterogeneous (i.e., mixed-attributes) data, we propose a novel kNN (k nearest neighbor) imputation method to iteratively imputing missing data, named GkNN (gray kNN) imputation. GkNN selects k nearest neighbors for each missing datum via calculating the gray distance between the missing datum and all the training data rather than traditional distance metric methods, such as Euclidean distance. Such a distance metric can deal with both numerical and categorical attributes. For achieving the better effectiveness, GkNN regards all the imputed instances (i.e., the missing data been imputed) as observed data, which with complete instances (instances without missing values) together to iteratively impute other missing data. We experimentally evaluate the proposed approach, and demonstrate that the gray distance is much better than the Minkowski distance at both capturing the proximity relationship (or nearness) of two instances and dealing with mixed attributes. Moreover, experimental results also show that the GkNN algorithm is much more efficient than existent kNN imputation methods.
Immune infiltration of tumors is closely associated with clinical outcome in renal cell carcinoma (RCC). Tumor‐infiltrating immune cells (TIICs) regulate cancer progression and are appealing ...therapeutic targets. The purpose of this study was to determine the composition of TIICs in RCC and further reveal the independent prognostic values of TIICs. CIBERSORT, an established algorithm, was applied to estimate the proportions of 22 immune cell types based on gene expression profiles of 891 tumors. Cox regression was used to evaluate the association of TIICs and immune checkpoint modulators with overall survival (OS). We found that CD8+ T cells were associated with prolonged OS (hazard ratio HR = 0.09, 95% confidence interval CI.01‐.53; P = 0.03) in chromophobe carcinoma (KICH). A higher proportion of regulatory T cells was associated with a worse outcome (HR = 1.59, 95% CI 1.23‐.06; P < 0.01) in renal clear cell carcinoma (KIRC). In renal papillary cell carcinoma (KIRP), M1 macrophages were associated with a favorable outcome (HR = .43, 95% CI .25‐.72; P < 0.01), while M2 macrophages indicated a worse outcome (HR = 2.55, 95% CI 1.45‐4.47; P < 0.01). Moreover, the immunomodulator molecules CTLA4 and LAG3 were associated with a poor prognosis in KIRC, and IDO1 and PD‐L2 were associated with a poor prognosis in KIRP. This study indicates TIICs are important determinants of prognosis in RCC meanwhile reveals potential targets and biomarkers for immunotherapy development.
We described the immune landscape in detail, revealing the distinct immune infiltration patterns of different subtypes and stages of RCC. We further revealed relationships between TIIC and molecular subtypes, tumor stages, recurrent genomic alterations and survival in RCC. Our work advances the understanding of immune response meanwhile reveals potential targets and biomarkers for immunotherapy development.
The study of EMG characteristics of high-level distance runners in limb flexion, extension, and their special exercise movements is beneficial to developing competitive distance running sports. In ...this study, high-level distance runners were used as the research object, and the sEMG test in EMG analysis was used to compare the general distance runners, and the changes of MPF, FC, and IEMG were obtained during the limb flexion, extension, and special exercise movements of high-level distance runners. When the FC was 100Hz, the MPF values of high-level distance runners were 64MV
/Hz, while the MPF values of average-distance runners were 45 MV
/Hz. When the muscle strength reached 50%, the IEMG values of rectus abdominis, biceps femoris, and gastrocnemius were 52%, 45 and 56%, respectively, in high-level distance runners, while the IEMG values of average distance runners were 47%, 42%, and 50%, respectively and 50%, respectively. Through the data analysis, the high-level long-distance runners could maintain a higher exercise state and perform at a stable level despite the gradual muscle fatigue, their muscle strength and contraction ability were stronger, and their explosive muscle power and potential were greater than the average long-distance runners.
In this paper, we propose a new unsupervised spectral feature selection model by embedding a graph regularizer into the framework of joint sparse regression for preserving the local structures of ...data. To do this, we first extract the bases of training data by previous dictionary learning methods and, then, map original data into the basis space to generate their new representations, by proposing a novel joint graph sparse coding (JGSC) model. In JGSC, we first formulate its objective function by simultaneously taking subspace learning and joint sparse regression into account, then, design a new optimization solution to solve the resulting objective function, and further prove the convergence of the proposed solution. Furthermore, we extend JGSC to a robust JGSC (RJGSC) via replacing the least square loss function with a robust loss function, for achieving the same goals and also avoiding the impact of outliers. Finally, experimental results on real data sets showed that both JGSC and RJGSC outperformed the state-of-the-art algorithms in terms of k -nearest neighbor classification performance.
Long short-term memory (LSTM) neural networks and attention mechanism have been widely used in sentiment representation learning and detection of texts. However, most of the existing deep learning ...models for text sentiment analysis ignore emotion's modulation effect on sentiment feature extraction, and the attention mechanisms of these deep neural network architectures are based on word- or sentence-level abstractions. Ignoring higher level abstractions may pose a negative effect on learning text sentiment features and further degrade sentiment classification performance. To address this issue, in this article, a novel model named AEC-LSTM is proposed for text sentiment detection, which aims to improve the LSTM network by integrating emotional intelligence (EI) and attention mechanism. Specifically, an emotion-enhanced LSTM, named ELSTM, is first devised by utilizing EI to improve the feature learning ability of LSTM networks, which accomplishes its emotion modulation of learning system via the proposed emotion modulator and emotion estimator. In order to better capture various structure patterns in text sequence, ELSTM is further integrated with other operations, including convolution, pooling, and concatenation. Then, topic-level attention mechanism is proposed to adaptively adjust the weight of text hidden representation. With the introduction of EI and attention mechanism, sentiment representation and classification can be more effectively achieved by utilizing sentiment semantic information hidden in text topic and context. Experiments on real-world data sets show that our approach can improve sentiment classification performance effectively and outperform state-of-the-art deep learning-based methods significantly.
Lithium-based batteries have had a profound impact on modern society through their extensive use in portable electronic devices, electric vehicles, and energy storage systems. However, battery safety ...issues such as thermal runaway, fire, and explosion hinder their practical application, especially for using metal anode. These problems are closely related to the high flammability of conventional electrolytes and have prompted the study of flame-retardant and nonflammable electrolytes. Here, we review the recent research on nonflammable electrolytes used in lithium-based batteries, including phosphates, fluorides, fluorinated phosphazenes, ionic liquids, deep eutectic solvents, aqueous electrolytes, and solid-state electrolytes. Their flame-retardant mechanisms and efficiency are discussed, as well as their influence on cell electrochemical performance. We conclude with a summary of future prospects for the design of nonflammable electrolytes and the construction of safer lithium-based batteries.
Display omitted
•This review compares the efficiency, stability and compatibility of various flame retardants.•The characteristic parameters of thermal runaway and their influence are illustrated.•Radical scavenging mechanism and characterization methods of flammability are summarized.•Inspiring further exploration in the design of nonflammable electrolytes toward safer lithium-based batteries.
The development history and principle of interwell tracer testing and single-well tracer testing were investigated, and the application conditions and application advantages of different tracer ...testing were analyzed through the analysis of two types of tracer testing technologies and test results in the production process of SMi oilfield with medium porosity and low permeability, so as to provide reference for the study of tracer development in the same type of oilfield. Tracer testing technology can master the connection between injection well and production well, effectively judge the connection relationship between Wells, and provide a basis for well pattern adjustment; The seepage velocity of injected fluid in the formation can be directly observed, and the dominant injection direction can be determined, which provides reference for solving the plane contradiction. It can judge whether there is fracture system or high permeability strip, which provides ideas for high precision numerical simulation to avoid risks. It can master the remaining oil situation of single well and judge the washing efficiency of chemical agents effectively on the basis of saving investment.
Particulate matter (PM) pollution has become a serious public health issue, especially with outbreaks of emerging infectious diseases. However, most present filters are bulky, opaque, and show ...low‐efficiency PM0.3/pathogen interception and inevitable trade‐off between PM removal and air permeability. Here, a unique electrospraying–netting technique is used to create spider‐web‐inspired network generator (SWING) air filters. Manipulation of the dynamic of the Taylor cone and phase separation of its ejected droplets enable the generation of 2D self‐charging nanostructured networks on a large scale. The resultant SWING filters show exceptional long‐range electrostatic property driven by aeolian vibration, enabling self‐sustained PM adhesion. Combined with their Steiner‐tree‐structured pores (size 200–300 nm) consisting of nanowires (diameter 12 nm), the SWING filters exhibit high efficiency (>99.995% PM0.3 removal), low air resistance (<0.09% atmosphere pressure), high transparency (>82%), and remarkable bioprotective activity for biohazard pathogens. This work may shed light on designing new fibrous materials for environmental and energy applications.
A spider‐web‐inspired network generator (SWING)‐based air filter constructed from 2D electrostatic nanostructured networks is created by a unique electrospraying–netting technique. Due to the self‐sustained electrostatic adhesion driven by aeolian vibration and Steiner‐tree‐structured pores (size 200–300 nm) consisting of nanowires (diameter 12 nm), the SWING filters achieve >99.995% PM0.3 removal, <0.09% atmosphere pressure, >82% transmittance, and remarkable bioprotective activity.
In image analysis, the images are often represented by multiple visual features (also known as multiview features), that aim to better interpret them for achieving remarkable performance of the ...learning. Since the processes of feature extraction on each view are separated, the multiple visual features of images may include overlap, noise, and redundancy. Thus, learning with all the derived views of the data could decrease the effectiveness. To address this, this paper simultaneously conducts a hierarchical feature selection and a multiview multilabel (MVML) learning for multiview image classification, via embedding a proposed a new block-row regularizer into the MVML framework. The block-row regularizer concatenating a Frobenius norm (F-norm) regularizer and an l 2,1 -norm regularizer is designed to conduct a hierarchical feature selection, in which the F-norm regularizer is used to conduct a high-level feature selection for selecting the informative views (i.e., discarding the uninformative views) and the 12,1-norm regularizer is then used to conduct a low-level feature selection on the informative views. The rationale of the use of a block-row regularizer is to avoid the issue of the over-fitting (via the block-row regularizer), to remove redundant views and to preserve the natural group structures of data (via the F-norm regularizer), and to remove noisy features (the 12,1-norm regularizer), respectively. We further devise a computationally efficient algorithm to optimize the derived objective function and also theoretically prove the convergence of the proposed optimization method. Finally, the results on real image datasets show that the proposed method outperforms two baseline algorithms and three state-of-the-art algorithms in terms of classification performance.
Robustness and discrimination are two of the most important objectives in image hashing. We incorporate ring partition and invariant vector distance to image hashing algorithm for enhancing rotation ...robustness and discriminative capability. As ring partition is unrelated to image rotation, the statistical features that are extracted from image rings in perceptually uniform color space, i.e., CIE L*a*b* color space, are rotation invariant and stable. In particular, the Euclidean distance between vectors of these perceptual features is invariant to commonly used digital operations to images (e.g., JPEG compression, gamma correction, and brightness/contrast adjustment), which helps in making image hash compact and discriminative. We conduct experiments to evaluate the efficiency with 250 color images, and demonstrate that the proposed hashing algorithm is robust at commonly used digital operations to images. In addition, with the receiver operating characteristics curve, we illustrate that our hashing is much better than the existing popular hashing algorithms at robustness and discrimination.
PDF
