Human activity recognition (HAR) aims to recognize activities from a series of observations on the actions of subjects and the environmental conditions. The vision-based HAR research is the basis of many applications including video surveillance, health care, and human-computer interaction (HCI). This review highlights the advances of state-of-the-art activity recognition approaches, especially for the activity representation and classification methods. For the representation methods, we sort out a chronological research trajectory from global representations to local representations, and recent depth-based representations. For the classification methods, we conform to the categorization of template-based methods, discriminative models, and generative models and review several prevalent methods. Next, representative and available datasets are introduced. Aiming to provide an overview of those methods and a convenient way of comparing them, we classify existing literatures with a detailed taxonomy including representation and classification methods, as well as the datasets they used. Finally, we investigate the directions for future research.

With the advances in technology, there has been an increasing interest from researchers and industrial institutions in the use of underwater wireless sensor networks (UWSNs). Constrained by the open acoustic channel, harsh underwater environment, and their own particularities, UWSNs are vulnerable to a wide class of security threats and malicious attacks. However, most existing research into UWSNs has not taken security into consideration. Moreover, the existing relatively mature security mechanisms for WSNs cannot be directly utilized in UWSNs. For these reasons, this article aims to present a comprehensive overview of the particularities, constraints, attacks, challenges and current security mechanisms of UWSNs. In addition, challenging, open and hot research topics are outlined.

With the preferable efficiency in storage and computation, hashing has shown potential application in large-scale multimedia retrieval. Compared with traditional hashing algorithms using hand-crafted characteristics, deep hashing inherits the representational capacity of deep neural networks to jointly learn semantic features and hash functions, encoding raw data into compact binary codes with significant discrimination. Generally, most of the current multi-wise hashing methods view the similarity margins between image pairs as constant values in training process. When the distance between sample pairs exceeds the fixed margin, the hashing network would not learn anything. Besides, available hashing methods commonly introduce the random sampling strategy to build training batches and ignore the sample distribution, which is harmful to parameter optimization. In this paper, we propose a novel Deep Adaptive Quadruplet Hashing with probability sampling (DAQH) for discriminative binary code learning. Specifically, with exploring the distribution relationship of raw samples, a non-uniform probability sampling strategy is proposed to build more informative and representative training batches, while maintaining the diversity of training samples. By introducing the prior similarity of sample pairs to calculate corresponding margins, an adaptive margin quadruplet loss is designed to dynamically preserve the underlying semantic relationships with its neighbors. To tune the attributes of binary codes, by combining quadruple regularization and orthogonality optimization, binary code constraint is developed to make the learned embedding with significant discrimination. Extensive experimental results on various benchmark datasets demonstrate our proposed DAQH framework achieves state-of-the-art visual similarity search performance.

Neuropathic pain is a debilitating pathological condition that presents significant therapeutic challenges in clinical practice. Unfortunately, current pharmacological treatments for neuropathic pain lack clinical efficacy and often lead to harmful adverse reactions. As G protein-coupled receptors (GPCRs) are widely distributed throughout the body, including the pain transmission pathway and descending inhibition pathway, the development of novel neuropathic pain treatments based on GPCRs allosteric modulation theory is gaining momentum. Extensive research has shown that allosteric modulators targeting GPCRs on the pain pathway can effectively alleviate symptoms of neuropathic pain while reducing or eliminating adverse effects. This review aims to provide a comprehensive summary of the progress made in GPCRs allosteric modulators in the treatment of neuropathic pain, and discuss the potential benefits and adverse factors of this treatment. We will also concentrate on the development of biased agonists of GPCRs, and based on important examples of biased agonist development in recent years, we will describe universal strategies for designing structure-based biased agonists. It is foreseeable that, with the continuous improvement of GPCRs allosteric modulation and biased agonist theory, effective GPCRs allosteric drugs will eventually be available for the treatment of neuropathic pain with acceptable safety.

In the process of drug discovery, identifying the interaction between the protein and the novel compound plays an important role. With the development of technology, deep learning methods have shown excellent performance in various situations. However, the compound–protein interaction is complicated and the features extracted by most deep models are not comprehensive, which limits the performance to a certain extent. In this paper, we proposed a multiscale convolutional network that extracted the local and global features of the protein and the topological feature of the compound using different types of convolutional networks. The results showed that our model obtained the best performance compared with the existing deep learning methods.