Search

Cross-media search from large-scale social network big data has become increasingly valuable in our daily life because it can support querying different data modalities. Deep hash networks have shown high potential in achieving efficient and effective cross-media search performance. However, due to the fact that social network data often exhibit text sparsity, diversity, and noise characteristics, the search performance of existing methods often degrades when dealing with this data. In order to address this problem, this article proposes a novel end-to-end cross-media semantic correlation learning model based on a deep hash network and semantic expansion for social network cross-media search (DHNS). The approach combines deep network feature learning and hash-code quantization learning for multimodal data into a unified optimization architecture, which successfully preserves both intramedia similarity and intermedia correlation, by minimizing both cross-media correlation loss and binary hash quantization loss. In addition, our approach realizes semantic relationship expansion by constructing the image-word relation graph and mining the potential semantic relationship between images and words, and obtaining the semantic embedding based on both internal graph deep walk and an external knowledge base. Experimental results demonstrate that DHNS yields better cross-media search performance on standard benchmarks.

Background Our trial aims to provide evidence for pain management and rehabilitation in patients with hemiplegic shoulder pain (HSP). HSP is one of the most common pains and disabilities occurring after a stroke. With accumulating evidence, the management of the suprascapular nerve (SSN) or axillary nerve (AN) might effectively relieve the pain and disability associated with HSP. However, no study has compared the effects of pulsed radiofrequency and nerve block of SSN and AN. Methods Twenty patients with chronic stroke (over one year from onset) and HSP [visual analog scale (VAS) for pain ≥30 mm] randomly underwent ultrasound-guided SSN and AN pulsed radiofrequency or nerve block treatment. All patients were evaluated before treatment (T0) and at 4 (T1) and 16 (T2) weeks of follow-up. The primary outcome was the VAS score. Secondary outcomes were the Modified Ashworth Scale (MAS) score, passive shoulder range of motion (PROM), Disability Assessment Scale (DAS) score, and EuroQol-5 dimension questionnaire (EQ-5D). Results Significant improvements in the VAS score were observed in both groups at T1 and T2. However, a significant difference was not observed between the two groups (T1: P=0.43; T2: P=0.23). No statistically significant differences were observed in the MAS score between the two groups at T1 (P=0.06) and T2 (P=0.07). In the PROM of shoulder abduction and external rotation, statistically, significant differences were observed between the two groups at T1 (P=0.02*, & P=0.04*) and T2 (P=0.02*, & P=0.00*). Statistically significant differences in shoulder flexion and extension were not observed between the two groups at T1 (P=0.23, & P=0.35) and T2 (P=0.14, & P=0.14). Statistically significant differences in the DAS score were not observed between the 2 groups at T1 (P=0.51, & P=0.33, & P=0.36, & P=0.75) and T2 (P=0.12, & P=0.54, & P=0.41, & P=0.86). No statistically significant differences in the EQ-5D responses were observed between the two groups at T1 (P=0.42) and T2 (P=0.11). Conclusions Pulsed radiofrequency of SSN and AN achieves similar therapeutic effects to the nerve block. Pulsed radiofrequency modulation is superior to nerve block in improving the PROM of shoulder abduction and external rotation.

With the rapid development of social network platforms, more and more people are using them to search for material related to their interests. As the texts of social media messages are usually so short, when traditional existing document modeling methods are used in social network search tasks, the problem of semantic sparsity arises, leading to low-quality semantic representation and low-precision social network search results. Fortunately, besides of short text, social media data also has other features, such as timestamps, locations, and its user information. In light of this, to realize precise social network search, we propose a multi-feature probabilistic graphical model (MFPGM), which can generate high-quality semantic representation. To deal with the problem of semantic sparsity, we exploit two strategies in MFPGM. First, we propose a concept named special region and utilize location information to aggregate short text into long text. Second, we introduce the biterm pattern that can generate dense semantic space by supposing that a biterm occurring in the same context has the same topic. In order to generate high-quality semantic representations, we simultaneously model multiple features (i.e., biterm, user, location and timestamp) of social network data to enhance the semantic learning process of MFPGM. We conduct a lot of experiments on real-word datasets, and the comparisons with several state-of-art baseline methods have demonstrated the superiority of our MFPGM on topic quality and search performance. Additionally, with the help of the generated semantic representations, MFPGM allows people to analyze the relationships between time and the popularities of topics.

Given the social network short text native sparsity, semantic inference becomes an infeasible task for conventional topic models. By exploiting the spatial and temporal characteristics of social network data, we propose a social network short text semantic modeling method, named by Spatial and Temporal Topic Model (STTM). To further overcome short text sparsity, STTM leverages co-occurrence word–word pair to reduce the sparsity problem, and moreover, it incorporates time information into the process of topics modeling in order to generate topics with higher quality. Experimental results over four real social media datasets verify the effectiveness of STTM.

Hashtag recommendation for microblogs is a very hot research topic that is useful to many applications involving microblogs. However, since short text in microblogs and low utilization rate of hashtags will lead to the data sparsity problem, it is difficult for typical hashtag recommendation methods to achieve accurate recommendation. In light of this, we propose HRMF, a hashtag recommendation method based on multi-features of microblogs in this article. First, our HRMF expands short text into long text, and then it simultaneously models multi-features (i.e., user, hashtag, text) of microblogs by designing a new topic model. To further alleviate the data sparsity problem, HRMF exploits hashtags of both similar users and similar microblogs as the candidate hashtags. In particular, to find similar users, HRMF combines the designed topic model with typical user-based collaborative filtering method. Finally, we realize hashtag recommendation by calculating the recommended score of each hashtag based on the generated topical representations of multi-features. Experimental results on a real-world dataset crawled from Sina Weibo demonstrate the effectiveness of our HRMF for hashtag recommendation.

Cross-media search is useful for getting more comprehensive and richer information about social network hot topics or events. To solve the problems of feature heterogeneity and semantic gap of different media data, existing deep cross-media quantization technology provides an efficient and effective solution for cross-media common semantic representation learning. However, due to the fact that social network data often exhibits semantic sparsity, diversity, and contains a lot of noise, the performance of existing cross-media search methods often degrades. To address the above issue, this paper proposes a novel fine-grained cross-media representation learning model with deep quantization attention network for social network cross-media search (CMSL). First, we construct the image-word semantic correlation graph, and perform deep random walks on the graph to realize semantic expansion and semantic embedding learning, which can discover some potential semantic correlations between images and words. Then, in order to discover more fine-grained cross-media semantic correlations, a multi-scale fine-grained cross-media semantic correlation learning method that combines global and local saliency semantic similarity is proposed. Third, the fine-grained cross-media representation, cross-media semantic correlations and binary quantization code are jointly learned by a unified deep quantization attention network, which can preserve both inter-media correlations and intra-media similarities, by minimizing both cross-media correlation loss and binary quantization loss. Experimental results demonstrate that CMSL can generate high-quality cross-media common semantic representation, which yields state-of-the-art cross-media search performance on two benchmark datasets, NUS-WIDE and MIR-Flickr 25k.

This article provides a review of the causes of respiratory tract infection after abdominal surgery. These causes include general anesthesia, intubation factors, factors inherent to the patient, surgical factors, the injudicious use of antimicrobial agents, and the environmental factors of the ward. The perioperative management of the respiratory tract should be strengthened. Health education, respiratory function training, oral nursing intervention, atomization inhalation, and personalized expectoration methods should receive more attention to decrease the complications and promote the early rehabilitation of patients after abdominal surgery.

Background Accumulating evidence indicates that spinal inflammatory and immune responses play an important role in the process of radicular pain caused by intervertebral disk herniation. Resolvin D1 (RvD1) has been shown to have potent antiinflammatory and antinociceptive effects. The current study was undertaken to investigate the analgesic effect of RvD1 and its underlying mechanism in rat models of noncompressive lumbar disk herniation. Methods Rat models of noncompressive lumber disk herniation were established, and mechanical thresholds were evaluated using the von Frey test during an observation period of 21 days (n = 8/group). Intrathecal injection of vehicle or RvD1 (10 or 100 ng) was performed for three successive postoperative days. On day 7, the ipsilateral spinal dorsal horns and L5 dorsal root ganglions (DRGs) were removed to assess the expressions of tumor necrosis factor-α (TNF-α), interleukin-1β (IL-1β), IL-10, and transforming growth factor-β1 (TGF-β1) and the activation of nuclear factor-κB (NF-κB)/p65 and phospho-extracellular signal–regulated kinase (p-ERK) signaling (n = 30/group). Results The application of nucleus pulposus to L5 DRG induced prolonged mechanical allodynia, inhibited the production of IL-10 and TGF-β1, and up-regulated the expression of TNF-α, IL-1β, NF-κB/p65, and p-ERK in the spinal dorsal horns and DRGs. Intrathecal injection of RvD1 showed a potent analgesic effect, inhibited the up-regulation of TNF-α and IL-1β, increased the release of IL-10 and TGF-β1, and attenuated the expression of NF-κB/p65 and p-ERK in a dose-dependent manner. Conclusions The current study showed that RvD1 might alleviate neuropathic pain via regulating inflammatory mediators and NF-κB/p65 and p-ERK pathways. Its antiinflammatory and proresolution properties may offer novel therapeutic approaches for the management of neuropathic pain.

Neuroinflammation induced by protruded nucleus pulposus (NP) has been shown to play a significant role in facilitation of radicular pain. Resolvin D2 (RvD2), a novel member of resolvin family, exhibits potent anti-inflammatory, pro-resolving and antinociceptive effects. But the effect of RvD2 in radicular pain remains unknown. The radicular pain rat models were induced by application of NP to L5 dorsal root ganglion. Each animal received intrathecal injections of vehicle or RvD2 (10 ng µl−1 or 100 ng µl−1). Mechanical thresholds were determined by measuring the paw withdrawal threshold for 7 days. The expressions of tumor necrosis factor-α (TNF-α), interleukin-6 (IL-6) and transforming growth factor-β1 (TGF-β1) in ipsilateral lumbar segment of rat spinal dorsal horns were measured by using ELISA and real time-PCR. Western blot was used to measure the expressions of phosphorylated Akt (p-Akt) and phosphorylated glycogen synthase kinase 3 beta (p-GSK-3β). The expressions and distributions of RvD2 receptor, G-protein-coupled receptor 18 (GPR18), were also explored in the spinal cord of rats by using double-label immunofluorescence. RvD2 treatment caused significant reductions in the intensity of mechanical hypersensitivity and spinal expressions of TNF-α and IL-6. Meanwhile, RvD2 increased the expressions of TGF-β1 and regulated Akt/GSK-3β signaling. Furthermore, immunofluorescence showed that GPR18 colocalized with neurons and astrocytes in spinal cord. The results suggested that RvD2 might attenuate mechanical allodynia via regulating the expressions of inflammatory mediators and activation of Akt/GSK-3β signal pathway. RvD2 might offer a hopeful method for radicular pain therapy.

Social network generates massive text data every day, which makes it important to mine its semantics. However, due to the inability to combine global semantics with local semantics, existing semantic modeling methods cannot overcome the sparseness of short texts and the ambiguity of words in different spatial-temporal environments. In this paper, we propose a semantic modeling method for social network short text, named Spatial-temporal topic embedding (STTE), which combines the spatial-temporal global context information and local context information. We first design a topic model that utilizes the text feature, time feature and location feature at the same time to generate accurate spatial-temporal global context information. Then, we employ this global information to predict an explicit topic for each word and regard the combination of each word and its assigned topic as a new pseudo word. After that, we exploit pseudo word sequence as the input of embedding vector model and finally learn the text feature which could reflect the text semantic with social network characteristics. Classification and search experiments in real-world datasets of the social network have verified that the proposed STTE has better semantic modeling ability than other baseline methods.