Human activity recognition (HAR) problems have traditionally been solved by using engineered features obtained by heuristic methods. These methods ignore the time information of the streaming sensor data and cannot achieve sequential human activity recognition. With the use of traditional statistical learning methods, results could easily plunge into the local minimum other than the global optimal and also face the problem of low efficiency. Therefore, we propose a hybrid deep framework based on convolution operations, LSTM recurrent units, and ELM classifier; the advantages are as follows: (1) does not require expert knowledge in extracting features; (2) models temporal dynamics of features; and (3) is more suitable to classify the extracted features and shortens the runtime. All of these unique advantages make it superior to other HAR algorithms. We evaluate our framework on OPPORTUNITY dataset which has been used in OPPORTUNITY challenge. Results show that our proposed method outperforms deep nonrecurrent networks by 6%, outperforming the previous reported best result by 8%. When compared with neural network using BP algorithm, testing time reduced by 38%.
Long noncoding RNAs (lncRNAs) play crucial roles in hepatocellular carcinoma (HCC). However, the underlying molecular mechanisms of small nucleolar RNA host gene 16 (SNHG16) for regulating the cell cycle and epithelial to mesenchymal transition (EMT) remain elusive. In this study, SNHG16 expression profiles of HCC tissues or cell lines were compared with those of normal tissues or hepatocyte cell line. The effect of SNHG16 knockdown in HCC cell lines was investigated by using in vitro loss-of-function experiments and in vivo nude mouse experiments. The potential molecular regulatory mechanism of SNHG16 in HCC progression was investigated by using mechanistic experiments and rescue assays. The results revealed that SNHG16 was highly expressed in HCC tissues and cell lines, which predicted poor prognosis of HCC patients. On one hand, the downregulation of SNHG16 induced G2/M cell cycle arrest, inducing cell apoptosis and suppression of cell proliferation. On the other hand, it inhibited cell metastasis and EMT progression demonstrated by in vitro loss-of-function cell experiments. Besides, knockdown of SNHG16 increased the sensitivity of HCC cells to cisplatin. For the detailed mechanism, SNHG16 was demonstrated to act as a let-7b-5p sponge in HCC. SNHG16 facilitated the G2/M cell cycle transition by directly acting on the let-7b-5p/CDC25B/CDK1 axis, and promoted cell metastasis and EMT progression by regulating the let-7b-5p/HMGA2 axis in HCC. In addition, the mechanism of SNHG16 for regulating HCC cell proliferation and metastasis was further confirmed in vivo by mouse experiments. Furthermore, these results can Shengguang Li and Fujun Peng contributed equally to this work.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.