Current local density-based anomaly detection methods are limited in that the local density estimation and the neighborhood density estimation are not accurate enough for complex and large databases, and the detection performance depends on the size parameter of the neighborhood. In this paper, we propose a new kernel function to estimate samples' local densities and propose a weighted neighborhood density estimation to increase the robustness to changes in the neighborhood size. We further propose a local kernel regression estimator and a hierarchical strategy for combining information from the multiple scale neighborhoods to refine anomaly factors of samples. We apply our general anomaly detection method to image saliency detection by regarding salient pixels in objects as anomalies to the background regions. Local density estimation in the visual feature space and kernel-based saliency score propagation in the image enable the assignment of similar saliency values to homogenous object regions. Experimental results on several benchmark datasets demonstrate that our anomaly detection methods overall outperform several state-of-art anomaly detection methods. The effectiveness of our image saliency detection method is validated by comparison with several state-of-art saliency detection methods.

Background: The study was to investigate the prevalence of metabolic health in subjects with obesity in the Chinese population and to identify the determinants related to metabolic abnormality in obese individuals. Methods: 5013 subjects were recruited from seven provincial capitals in China. The obesity and metabolic status were classified based on body mass index (BMI) and the number of abnormalities in common components of metabolic syndrome. Results: 27.9% of individuals with obesity were metabolically healthy. The prevalence of the metabolically healthy obese (MHO) phenotype was significantly decreased with age in women (p _trend < 0.001), but not significantly in men (p _trend = 0.349). Central obesity (odds ratio [OR] = 4.07, 95% confidence interval [CI] = 1.93–8.59), longer sedentary time (OR = 1.97, 95%CI = 1.27–3.06), and with a family history of obesity related diseases (hypertension, diabetes, dyslipidemia) (OR = 1.85, 95%CI = 1.26–2.71) were significantly associated with having metabolic abnormality in obese individuals. Higher levels of physical activity and more fruit/vegetable intake had decreased ORs of 0.67 (95%CI = 0.45–0.98) and 0.44 (95%CI = 0.28–0.70), respectively. Conclusion: 27.9% of obese participants are in metabolic health. Central obesity, physical activity, sedentary time, fruits/vegetables intake and family history of diseases are the determinants associated with metabolic status in obesity.

Clustering aggregation, known as clustering ensembles, has emerged as a powerful technique for combining different clustering results to obtain a single better clustering. Existing clustering aggregation algorithms are applied directly to data points, in what is referred to as the point-based approach. The algorithms are inefficient if the number of data points is large. We define an efficient approach for clustering aggregation based on data fragments. In this fragment-based approach, a data fragment is any subset of the data that is not split by any of the clustering results. To establish the theoretical bases of the proposed approach, we prove that clustering aggregation can be performed directly on data fragments under two widely used goodness measures for clustering aggregation taken from the literature. Three new clustering aggregation algorithms are described. The experimental results obtained using several public data sets show that the new algorithms have lower computational complexity than three well-known existing point-based clustering aggregation algorithms (Agglomerative, Furthest, and LocalSearch); nevertheless, the new algorithms do not sacrifice the accuracy.

Sentiment analysis is a key component in various text mining applications. Numerous sentiment classification techniques, including conventional and deep-learning-based methods, have been proposed in the literature. In most existing methods, a high-quality training set is assumed to be given. Nevertheless, constructing a high-quality training set that consists of highly accurate labels is challenging in real applications. This difficulty stems from the fact that text samples usually contain complex sentiment representations, and their annotation is subjective. We address this challenge in this study by leveraging a new labeling strategy and utilizing a two-level long short-term memory network to construct a sentiment classifier. Lexical cues are useful for sentiment analysis, and they have been utilized in conventional studies. For example, polar and negation words play important roles in sentiment analysis. A new encoding strategy, that is, ρ-hot encoding, is proposed to alleviate the drawbacks of one-hot encoding and, thus, effectively incorporate useful lexical cues. Moreover, the sentimental polarity of a word may change in different sentences due to label noise or context. A flipping model is proposed to model the polar flipping of words in a sentence. We compile three Chinese datasets on the basis of our label strategy and proposed methodology. Experiments demonstrate that the proposed method outperforms state-of-the-art algorithms on both benchmark English data and our compiled Chinese data.

Aspect-based sentiment analysis (ABSA) is crucial for exploring user feedbacks and preferences on produces or services. Although numerous classical deep learning-based methods have been proposed in previous literature, several useful cues (e.g., contextual, lexical, and syntactic) are still not fully considered and utilized. In this study, a new approach for ABSA is proposed through the guidance of contextual, lexical, and syntactic cues. First, a novel sub-network is introduced to represent a target in a sentence in ABSA by considering the whole context. Second, lexicon embedding is applied to incorporate additional lexical cues. Third, a new attention module, namely, dependency attention, is proposed to elaborate syntactic dependency cues between words in attention inference. Experimental results on four benchmark data sets demonstrate the effectiveness of our proposed approach to aspect-based sentiment analysis.

Background: According to the validation literature on items of Young’s Internet Addiction Test (IAT), this study rephrased disputable items to improve the psychometric properties of this Chinese version of IAT and identify the presence of differential item function (DIF) among demographic and Internet use factors; detect the effect of demographic and Internet use factors on IAT after adjusting for DIF. Methods: An online questionnaire was distributed to college students in Zhe Jiang province in two stage. The 1st phase study collected 384 valid responses to examine the quality of IAT items by using Rasch Model analysis and exploring factor analysis (EFA). The online questionnaire was modified according to the 1st phase study and distributed online for the 2nd phase study which collected a total of 1131 valid responses. The 2nd phase study applied confirmatory factor analysis (CFA) and a multiple indicator multiple causes (MIMIC) model to verify the construct of IAT, potential effect of covariates on IAT latent factors, as well as the effect of differential item functioning (DIF). Results: Rasch model analysis in the 1st phase study indicated a 5-point rating scale was performed better, no sever misfit was found on item. The overall property of Chinese version IAT with the 5-point scale was good to excellent person and item separation (2.66 and 6.86). A three-factor model was identified by EFA. In the 2nd phase study, IAT 13 were detected with DIF for gender in MIMIC model. After correcting DIF effect, the significant demographic and Internet use factors on IAT were time spent online per day, year 3, year 2, general users. Conclusion: Item improvement was efficient that the problematic items found in literature was performed good in this study. The overall psychometric property of this Chinese version IAT was good with limited DIF effect in one item. Item improvement on IAT13 was encouraged in the future study to avoid gender bias and benefit for epidemiology on PIU.