RGB-induced salient object detection has recently witnessed substantial progress, which is attributed to the superior feature learning capability of deep convolutional neural networks (CNNs). However, such detections suffer from challenging scenarios characterized by cluttered backgrounds, low-light conditions and variations in illumination. Instead of improving RGB based saliency detection, this paper takes advantage of the complementary benefits of RGB and thermal infrared images. Specifically, we propose a novel end-to-end network for multimodal salient object detection, which turns the challenge of RGB-T saliency detection to a CNN feature fusion problem. To this end, a backbone network (e.g., VGG-16) is first adopted to extract the coarse features from each RGB or thermal infrared image individually, and then several adjacent-depth feature combination (ADFC) modules are designed to extract multi-level refined features for each single-modal input image, considering that features captured at different depths differ in semantic information and visual details. Subsequently, a multi-branch group fusion (MGF) module is employed to capture the crossmodal features by fusing those features from ADFC modules for a RGB-T image pair at each level. Finally, a joint attention guided bi-directional message passing (JABMP) module undertakes the task of saliency prediction via integrating the multi-level fused features from MGF modules. Experimental results on several public RGB-T salient object detection datasets demonstrate the superiorities of our proposed algorithm over the state-of-the-art approaches, especially under challenging conditions, such as poor illumination, complex background and low contrast.

No abstract

Compared to freshwater electrolysis, seawater electrolysis to produce hydrogen is preferable and more promising, but this technology is plagued by the electrode’s corrosion and oxidative reactions of the competitive Cl– ion on the anode. To develop efficient oxygen evolution reaction (OER) catalysts for seawater electrolysis, the ultrathin MnO x film-covered NiFe-layered double-hydroxide nanosheet array is directly assembled on Ni foam (MnO x /NiFe-LDH/NF) by hydrothermal and electrodeposition in turn. This catalyst demonstrates excellent OER-selective activity in alkaline saline electrolytes. In 1 M KOH/0.5 M NaCl and 1 M KOH/seawater electrolytes, MnO x /NiFe-LDH/NF exhibits lower overpotentials at 100 mA cm–2 (η100 values of 265 and 276 mV, respectively) and Tafel slopes (73 and 77 mV decade–1, respectively) than does the NiFe-LDH/NF electrode (η100 values of 298 and 327 mV and Tafel slopes of 91 and 140 mV decade–1, respectively). In alkaline saline solutions, the stability and durability of the former are also better than those of the latter. The good OER selectivity and catalytic performance are attributed to the MnO x overlayer that selectively blocks Cl– anions from approaching catalytic centers, and the good conductivity, fast kinetics, more oxygen vacancies, and abundant active sites of MnO x /NiFe-LDH/NF. The robust stability is due to the enhanced resistance for Cl– corrosion stemming from the MnO x protective film. Hence, MnO x /NiFe-LDH/NF can act as a promising OER electrocatalyst for alkalized natural seawater electrolysis.

No abstract

Sludge bio-drying in which sludge is dried by means of the heat generated by the aerobic degradation of its own organic substances has been widely used for sludge treatment. A better understanding of the evolution of dissolved organic matter (DOM) and its degradation drivers during sludge bio-drying could facilitate its control. Aeration is one of the key factors that affect sludge bio-drying performance. In this study, two aeration strategies (pile I-the optimized and pile II-the current) were established to investigate their impacts on the evolution of DOM and the microbial community in a full-scale sludge bio-drying plant. A higher pile temperature in pile I caused pile I to enter the DOM and microbiology stable stage approximately2 days earlier than pile II. The degradation of easily degradable components in the DOM primarily occurred in the thermophilic phase; after that degradation, the DOM components changed a little. Along with the evolution of the DOM, its main degradation driver, the microbial community, changed considerably. Phyla Firmicutes and Proteobacteria were dominant in the thermophilic stage, and genus Ureibacillus, which was the primary thermophilic bacteria, was closely associated with the degradation of the DOM. In the mesophilic stage, the microbial community changed significantly at first and subsequently stabilized, and the genus Parapedobacter, which belongs to Bacteriodetes, became dominant. This study elucidates the interplay between the DOM and microbial community during sludge bio-drying.

No abstract

As an artificial neural network method, self-organizing mapping facilities efficient complete and visualize high-dimensional data topology representation, valid in a number of applications such as network intrusion detection. However, there remains a challenge to accurately depict the topology of network traffic data with unbalanced distribution, which deteriorates the performance of e.g. DoS attack detection. Hence, we propose a new model of the ''statistic-enhanced directed batch growth self-organizing mapping'', renew the definition of the growth threshold used to evaluate/control neuron expansion, and first introduce the inner distribution factor for fine-grained data distinguishing. The numerical experiments based on two datasets, KDD99, and CICIDS2017, demonstrate that the key performance in DoS attack detection including the detection rate, the false positive rate, and the training time are greatly enhanced thanks to the statistic concepts consulted in the proposed model. INDEX TERMS DoS attack detection, statistic-enhanced directed batch growing self-organizing mapping, growth threshold, inner distribution factor.

No abstract