No abstract

Profile inference of SNS users is valuable for marketing, target advertisement, and opinion polls. Several studies examining profile inference have been reported to date. Although information of various types is included in SNS, most such studies only use text information. It is expected that incorporating information of other types into text classifiers can provide more accurate profile inference. As described in this paper, we propose combined method of text processing and image processing to improve gender inference accuracy. By applying the simple formula to combine two results derived from a text processor and an image processor, significantly increased accuracy was confirmed.

No abstract

Keyword-based tags (referred to as tags) are used to represent additional attributes of nodes in addition to what is explicitly stated in their contents, like the hashtags in YouTube. Aside of being auxiliary information for node representation, tags can also be used for retrieval, recommendation, content organization, and event analysis. Therefore, tag representation learning is of great importance. However, to learn satisfactory tag representations is challenging because 1) traditional representation methods generally fail when it comes to representing tags, 2) bidirectional interactions between nodes and tags should be modeled, which are generally not dealt within existing research works. In this paper, we propose a tag representation learning model which takes tag-related node interaction into consideration, named Tag2Gauss. Specifically, since tags represent node communities with intricate overlapping relationships, we propose that Gaussian distributions would be appropriate in modeling tags. Considering the bidirectional interactions between nodes and tags, we propose a tag representation learning model mapping tags to distributions consisting of two embedding tasks, namely Tag-view embedding and Node-view embedding. Extensive evidence demonstrates the effectiveness of representing tag as a distribution, and the advantages of the proposed architecture in many applications, such as the node classification and the network visualization.

Osteosarcoma is difficult to be resected through surgical operations without damage to the bone matrix, while chemotherapy and radiotherapy induce inevitable systemic injury. It is still a major challenge to develop a novel treatment suitable for the complex anatomical structure of the bone. Herein, inspired by lotus seedpods, injectable hydrogels with long-term retention for synergistic osteosarcoma treatment were developed. Gold nanoclusters (GNCs) with strong fluorescence (FL) and computed tomography (CT) imaging effects represented the lotus seeds. The oxidized hyaluronic acid (HA-ALD) chain resembled the stem. HA-ALD and GNCs form crosslinking-assembled hydrogels abbreviated as HG-CAHs through dynamic amide bonds. Compared with DNA-, pH-, and light-mediated assembly, this in situ method induces enhanced photothermal therapy (PTT) ability, ensures high biocompatibility, and retains the imaging function of GNCs, which contribute to lighting up osteosarcoma persistently for further diagnosis and treatment. In addition, the HG-CAHs with outstanding mechanical properties are similar to the lotus seedpods with supportive force and a typical porous structure. They are favorable for the local pH- and near-infrared (NIR)-responsive release of doxorubicin (Dox) owing to the acidic osteosarcoma microenvironment and the Brownian movement. The HG-CAHs ablate osteosarcoma efficiently and reduce metabolic toxicity significantly, which will aid in the development of a new generation of osteosarcoma treatments.

In the industrial internet of things (IIoT), because thousands of pieces of hardware, instruments, and various controllers are involved, the core problem is the sensors. Detection using sensors is the bottom line of the IIoT, directly affecting the detection accuracy and control indicators of the IIoT system. However, when a large number of realtime data generated by IIoT devices are transferred to cloud computing centers, large-scale data will inevitably bring computing load, which will affect the computing speed of cloud computing centers and increase the computing load of cloud computing data centers. These factors directly lead to instability and delay in sensor data collected in real time in the IIoT. In this paper, a sensor outlier detection algorithm based on edge calculation is proposed. Firstly, focusing on the problem of the large amount of data in terminal equipment of the IIoT, the edge technology method of data compression is used to optimize the compression of sensor data, and different thresholds are set according to different industrial process requirements, so as to ensure the real-time aspect and authenticity of the data. Then, using the K-means clustering algorithm, the compressed test data sets are analyzed and the abnormal sensor detection values and labels are obtained. Finally, the effectiveness of such an approach is evaluated through a sample case study involving a temperature control system.

No abstract

No abstract