Depression is a major contributor to the overall global burden of diseases. Traditionally, doctors diagnose depressed people face to face via referring to clinical depression criteria. However, more than 70% of the patients would not consult doctors at early stages of depression, which leads to further deterioration of their conditions. Meanwhile, people are increasingly relying on social media to disclose emotions and sharing their daily lives, thus social media have successfully been leveraged for helping detect physical and mental diseases. Inspired by these, our work aims to make timely depression detection via harvesting social media data. We construct well-labeled depression and non-depression dataset on Twitter, and extract six depression-related feature groups covering not only the clinical depression criteria, but also online behaviors on social media. With these feature groups, we propose a multimodal depressive dictionary learning model to detect the depressed users on Twitter. A series of experiments are conducted to validate this model, which outperforms (+3% to +10%) several baselines. Finally, we analyze a large-scale dataset on Twitter to reveal the underlying online behaviors between depressed and non-depressed users.
Osteoblastic lineage cells are commonly used to evaluate the in vitro osteogenic ability of bone biomaterials. However, contradictory results obtained from in vivo and in vitro studies are not uncommon. With the increasing understanding of osteoimmunology, the immune response has been recognized as playing an important role in bone regeneration. In this study, we examined the effect of submicron-scaled titanium surface roughness (ranging from approximately 100 to 400 nm) on the response of osteoblasts and macrophages. The results showed that osteoblast differentiation enhanced with increased surface roughness of titanium substrates. The cytoskeleton of macrophages altered with the variation in titanium surface roughness. The production of cytokines (TNF-α, IL-6, IL-4 and IL-10) could be regulated by titanium surface roughness. Moreover, macrophages cultured on titanium surfaces exhibited a tendency to polarize to M1 phenotype with the increase of surface roughness. Material/macrophage conditioned medium tended to promote osteoblast differentiation with the increase of surface roughness. The results indicate that increasing surface roughness in the submicron range is beneficial for osteogenesis via modulating the immune response of macrophages. Modifying biomaterial surfaces based on their immunomodulatory effects is considered as a novel strategy for the improvement of their biological performance.
Direct formate fuel cells (DFFCs) as promising energy technologies have been applied for portable and wearable devices. However, for the formate oxidation reaction (FOR), the deficiency of catalysts has prevented DFFCs from practical applications. Herein, we prepared a Pd-loaded CeO2 catalyst through a simple steam treatment at 400 °C to enhance the catalytic FOR performance. In comparison with the counterpart of Pd/CeO2 without stream treatment, the as-prepared Pd/CeO2-ST catalyst has a lower onset potential of 381 mV and a lower peak potential of 0.64 V with a higher peak current of 10.62 mA cm–2. The experimental results show that the enhanced FOR properties of Pd/CeO2-ST are ascribed to the introduction of surface reactive oxygen species to the CeO2 substrate, which substantially promotes the desorption of adsorbed hydrogen (H*) intermediates. Density functional theory (DFT) calculations reveal that on the surface of CeO2, the abundant oxygen vacancies boost the OH* adsorption ability and accelerate the kinetics of the potential-limiting step. This work not only proposes a new strategy for enhancing the activity of FOR catalysts but also highlights the understanding of the FOR mechanism in alkaline media for DFFC applications.
Machine learning has been widely applied to building security applications. However, many machine learning models require the continuous supply of representative labeled data for training, which limits the models' usefulness in practice. In this paper, we use bot detection as an example to explore the use of data synthesis to address this problem. We collected the network traffic from 3 online services in three different months within a year (23 million network requests). We develop a streambased feature encoding scheme to support machine learning models for detecting advanced bots. The key novelty is that our model detects bots with extremely limited labeled data. We propose a data synthesis method to synthesize unseen (or future) bot behavior distributions. The synthesis method is distributionaware, using two different generators in a Generative Adversarial Network to synthesize data for the clustered regions and the outlier regions in the feature space. We evaluate this idea and show our method can train a model that outperforms existing methods with only 1% of the labeled data. We show that data synthesis also improves the model's sustainability over time and speeds up the retraining. Finally, we compare data synthesis and adversarial retraining and show they can work complementary with each other to improve the model generalizability.
Human action recognition is an important recent challenging task. Projecting depth images onto three depth motion maps (DMMs) and extracting deep convolutional neural network (DCNN) features are discriminant descriptor features to characterize the spatiotemporal information of a specific action from a sequence of depth images. In this paper, a unified improved collaborative representation framework is proposed in which the probability that a test sample belongs to the collaborative subspace of all classes can be well defined and calculated. The improved collaborative representation classifier (ICRC) based on 2 -regularized for human action recognition is presented to maximize the likelihood that a test sample belongs to each class, then theoretical investigation into ICRC shows that it obtains a final classification by computing the likelihood for each class. Coupled with the DMMs and DCNN features, experiments on depth image-based action recognition, including MSRAction3D and MSRGesture3D datasets, demonstrate that the proposed approach successfully using a distance-based representation classifier achieves superior performance over the state-of-the-art methods, including SRC, CRC, and SVM.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.