Search

Air pollution is growing ever more serious as a result of rising consumption of energy and other natural resources. Generally, governmental static monitoring stations provide accurate air pollution data, but they are sparsely distributed in the space. In contrast, microstations as a kind of low-cost air monitoring equipment can be distributed densely though their accuracy is relatively low. This article proposes a deep calibration method (DeepCM) for low-cost air monitoring sensors equipped in the microstations, which consists of an encoder and a decoder. In the encoding stage, multilevel time-series features are extracted, including local, global, and periodic time-series features. These features can not only capture local, global, and periodic trend information, but also benefit to alleviating cross-interference and noise effect. In the decoding stage, a final feature extracted by the encoder along with initial features of the moment to be calibrated are fed into the decoder to obtain a calibrated result. The proposed method is evaluated on two real-world datasets. The experimental results demonstrate that our method yields the best performance by comparison with eight baseline methods. [ABSTRACT FROM AUTHOR]

[Display omitted] • Red mud supported Co 3 O 4 quantum dots are prepared via a facile method. • Co 3 O 4 QDs are uniformly anchored on RM to activate PMS under visible light. • The radical species in Co 3 O 4 /RM/PMS/Vis system have been investigated. • The degradation pathway of LVF and the toxicity study have been presented. • Reasons for the low leaching and high activity of composite have been given. In this work, iron-rich red mud (RM), a industrial waste generated from alumina production by Bayer process, was used as a potential carrier for supporting Co 3 O 4 quantum dots (QDs). A novel heterogeneous catalyst of RM-based Co 3 O 4 QDs (Co 3 O 4 /RM) composite was prepared via a simple method and used for the activation of peroxymonosulfate (PMS) under visible light (Vis) to degrade levofloxacin (LVF). The characterization results demonstrated that in-situ growth of Co 3 O 4 QDs on the surface of RM could increase the surface area, reduce the aggregation, enhance the visible light response and accelerate the separation of photogenerated electron-hole pairs, all of which effectively improved the catalytic activity of Co 3 O 4 /RM composite. Approximately 95.3 % of LVF was decomposed at 20 min in the PMS/Vis system catalyzed by the optimal Co 3 O 4 /RM-1200 composite. Both SO 4 ·- and h+ generated in Co 3 O 4 /RM-1200/PMS/Vis system were responsible for the rapid LVF degradation; especially the SO 4 ·- was the dominant active specie. Based on LC-MS technology and DFT calculation, the reasonable degradation pathways of LVF in Co 3 O 4 /RM-1200/PMS/Vis system were proposed. The ecotoxicity of degradation intermediates was evaluated according to the Toxicity Estimation Software Tool (T.E.S.T.) software. In addition, critical influencing factors on the degradation of LVF in Co 3 O 4 /RM-1200/PMS/Vis system were investigated. Exhilaratingly, it was found that the Co 3 O 4 QDs were deposited homogeneously on the surface of RM with the Fe-O-Co bond between Co 3 O 4 component and Fe 2 O 3 component, which not only prevented the leaching of metal ions but also contributed to the superior stability and reusability. This work has designed a new perspective for the development of a cost-efficiency and stable RM-based Co 3 O 4 QDs catalyst to activate PMS under visible light for the degradation of LVF. [ABSTRACT FROM AUTHOR]

Unsupervised person re-identification (ReID) aims at training a model through using fully unlabeled training images. Most successful approaches combine clustering-based pseudo-label prediction with ReID model learning and perform the two steps in an alternating fashion. However, there are some person images, which have common appearance but different identities or have same identity but large intra-variations, and they are prone to be assigned wrong pseudo-labels. Existing methods typically infer person image pseudo-labels in a single pseudo-label space, which is insufficient due to losing the accurate labels of these hard images. This limits model's power to cope with varying changes. To address this problem, we propose a Multi-granularity Pseudo-label Collaboration (MPC) method for unsupervised person ReID. Firstly, a multi-granularity pseudo-label prediction (MPP) method is proposed to predict the pseudo-labels of person images. MPP generates multiple pseudo-label spaces with each one inferring the person image pseudo-labels under a different granularity at cluster size. Secondly, the multiple pseudo-label spaces are applied to learn a mixture of experts (MoE) model. Each expert model is supervised by the pseudo-labels in a specific pseudo-label space, enabling MoE model to handle different variations. The output of these expert models are fused critically by a bilateral attention aggregation (BAA) to generate aggregation image features. Meanwhile, a label mix-up method is designed for refining pseudo-labels. It fuses labels across different pseudo-label spaces based on label co-occurrence to promote aggregation feature learning. We extensively evaluate the proposed MPC method under both image-based and video-based unsupervised person ReID settings. MPC significantly improves the current baseline method by a margin of 5.4% and 3.7% in mAP, and 3.4% and 3.9% in Rank1 accuracy on the image-based datasets Market-1501 and DukeMTMC-ReID, respectively. In particular, MPC method achieves state-of-the-art performance on video-based datasets with mAP of 71.4% and 87.3% on MARS and DukeMTMC-VideoReID, respectively. • A Multi-granularity Pseudo-label Collaboration (MPC) method is proposed for unsupervised person ReID. • A bilateral attention aggregation (BAA) module is developed to generate robust and diverse aggregation feature. • A label mix-up method with label co-occurrence is presented to produce refined labels to facilitate aggregation feature learning. • Extensive experiments verify the effectiveness of the proposed method on image-based and video-based two unsupervised person ReID settings. [ABSTRACT FROM AUTHOR]

Relevance feedback is an efficient approach to improve the performance of content-based image retrieval systems, and implicit relevance feedback approaches, which gather users' feedback by biometric devices (e.g. eye tracker), have extensively investigated in recent years. This paper proposes a novel image retrieval system with implicit relevance feedback, named eye tracking based relevance feedback system (ETRFs). ETRFs is composed of three main modules: image retrieval subsystem based on bag-of-word architecture; user relevance assessment that implicitly acquires relevant images with the help of a modern eye tracker; and relevance feedback module that applies a weighted query expansion method to fuse users' relevance feedback. ETRFs is implemented online and real-time, which makes it remarkably distinguish from other offline systems. Ten subjects participate our experiments on the dataset of Oxford buildings and UKBench. The experimental results demonstrate that ETRFs achieves notable improvement for image retrieval performance. [ABSTRACT FROM AUTHOR]