With the development of the Internet of Things (IoT) technology, its application in the medical field becomes more and more extensive. However, with a dramatic increase in medical data obtained from the IoT-based health service system, labeling a large number of medical data requires high cost and relevant domain knowledge. Therefore, how to use a small number of labeled medical data reasonably to build an efficient and high-quality clinical decision support model in the IoT-based platform has been an urgent research topic. In this paper, we propose a novel semi-supervised learning approach in association with generative adversarial networks (GANs) for supporting clinical decision making in the IoT-based health service system. In our approach, GAN is adopted to not only increase the number of labeled data but also to compensate the imbalanced labeled classes with additional artificial data in order to improve the semi-supervised learning performance. Extensive evaluations on a collection of benchmarks and real-world medical datasets show that the proposed technique outperforms the others and provides a potential solution for practical applications.

Peneciraistin C (Pe-C) is a novel spiroketal compound isolated from the saline soil derived fungus Penicillium raistrickii. Our previous study showed that Pe-C exerted a potent cytotoxic effect on many kinds of cancer cell lines, especially on human lung cancer A549 cells. Here, we report the anticancer mechanisms of Pe-C in a variety of lung cancer cells. The results showed that Pe-C induced caspase-independent autophagic cell death and elevated mitochondrial-derived reactive oxygen species levels. Interestingly, if autophagy was blocked by 3-methyladenine or Atg5 siRNA, Pe-C triggered a shift from autophagic cell death into caspase-dependent apoptotic cell death. In addition, cotreatment with the antioxidant N-acetyl-L-cysteine or Mito-TEMPO could effectively reverse the effect of the enhanced reactive oxygen species production, which in turn almost completely prevented the cell death induced by Pe-C. Thus, this study provided new insights into the mechanisms underlying Pe-C-mediated cell death, which indicated that Pe-C could be a potential drug candidate for therapy of lung cancers. (Cancer Sci 2013; 104: 1476-1482 L ung cancer is the leading cause of cancer-related death in men and is second only to breast cancer in women.(1,2) In China, approximately 60 0000 people suffer from this disease and consequently die each year. In clinical practice, lung carcinomas are classified into two major types: non-small-cell lung cancer and small-cell lung cancer.(3) Chemotherapy is still an important option in curing or controlling lung cancer. Although many relatively effective chemotherapeutic agents have been developed, the cure rate of lung cancer is still low because of drug resistance. In addition, the side-effects of chemotherapeutic drugs often hamper the quality of life of lung cancer patients.(4) Therefore, the discovery of effective novel molecular targeted therapies for lung cancer is urgently needed.Spiroketals are cyclic substructures found in many natural products that show a wide range of biological activities, such as antitumor activity, antibacterial activity, and anti-inflammatory effects.(5-8) Peneciraistin C (Pe-C) (Fig. 1) is a novel spiroketal compound purified from the fungus Penicillium raistrickii, isolated from saline soil collected in Bohai Bay in Zhanhua (Shandong Province, China). In preliminary screening, Pe-C showed potent cytotoxic activity in many kinds of human cancer cell lines, especially in human lung cancer A549 cells. (9) In this study, we report the antitumor activity and the possible molecular mechanisms of Pe-C in a variety of lung cancer cells.Over the past decades, apoptosis induction is the main focus in the development of new anticancer drugs, so a great number of studies have been focused on type-I programmed cell death. In contrast, more and more evidence now shows that autophagic cell death has emerged as an important mechanism of cancer cell death induced by anticancer agents.(10-12) The housekeeping role of autophagy is to protect cells under stressful conditions throug...

In recent years, the research of combining a knowledge graph with recommendation systems has caused widespread concern. By studying the interconnections in knowledge graphs, potential connections between users and items can be discovered, which provides abundant and complementary information for recommendation of items. However, most existing studies have not effectively established the relation between entities and users. Therefore, the recommendation results may be affected by some unrelated entities. In this paper, we propose a neighborhood aggregation collaborative filtering (NACF) based on knowledge graph. It uses the knowledge graph to spread and extract the user’s potential interest, and iteratively injects them into the user features with attentional deviation. We conducted a large number of experiments on three public datasets; we verifyied that NACF is ahead of the most advanced models in top-k recommendation and click-through rate (CTR) prediction.

Biologically inspired ideas are important in image processing. Not only does more than 80% of the information received by humans comes from the visual system, but the human visual system also gives its fast, accurate, and efficient image processing capability. In the current image classification task, convolutional neural networks (CNNs) focus on processing pixels and often ignore the semantic relationships and human brain mechanisms. With the development of image analysis and processing techniques, the information in the image is becoming increasingly complicated. Humans can learn about the characteristics of objects and the relationships that occur between them to classify the images. It is a significant characteristic that sets humans apart from the modern learning-based computer vision algorithms. How to make full use of the semantic relationships in categories and how to apply the knowledge of biological vision to image classification are our main concerns. In this view, we propose the concept of the image knowledge graph (IKG) to incorporate the semantic association and the scene association to fully consider the relations between objects (external and internal). We take full advantage of the reasoning model of the knowledge graph that is closer to the biological visual information-processing model. We conduct extensive experiments on large-scale image datasets (ImageNet), demonstrating the effectiveness of our approach. Furthermore, our method participates in ILSVRC 2017 challenges and obtains the new state-of-the-art results on the ImageNet (82.43%).