Automatic seizure detection is of great significance for epilepsy long-term monitoring, diagnosis, and rehabilitation, and it is the key to closed-loop brain stimulation. This paper presents a novel wavelet-based automatic seizure detection method with high sensitivity. The proposed method first conducts wavelet decomposition of multi-channel intracranial EEG (iEEG) with five scales, and selects three frequency bands of them for subsequent processing. Effective features are extracted, such as relative energy, relative amplitude, coefficient of variation and fluctuation index at the selected scales, and then these features are sent into the support vector machine for training and classification. Afterwards a postprocessing is applied on the raw classification results to obtain more accurate and stable results. Postprocessing includes smoothing, multi-channel decision fusion and collar technique. Its performance is evaluated on a large dataset of 509 h from 21 epileptic patients. Experiments show that the proposed method could achieve a sensitivity of 94.46% and a specificity of 95.26% with a false detection rate of 0.58/h for seizure detection in long-term iEEG.

Many real world applications are of time-varying nature and an online learning algorithm is preferred in tracking the realtime changes of the time-varying system. Online sequential extreme learning machine (OSELM) is an excellent online learning algorithm, and some improved OSELM algorithms incorporating forgetting mechanism have been developed to model and predict the time-varying system. But the existing algorithms suffer from a potential risk of instability due to the intrinsic ill-posed problem; besides, the adaptive tracking ability of these algorithms for complex time-varying system is still very weak. In order to overcome the above two problems, this paper proposes a novel OSELM algorithm with generalized regularization and adaptive forgetting factor (AFGR-OSELM). In the AFGR-OSELM, a new generalized regularization approach is employed to replace the traditional exponential forgetting regularization to make the algorithm have a constant regularization effect; consequently the potential illposed problem of the algorithm can be completely avoided and a persistent stability can be guaranteed. Moreover, the AFGR-OSELM adopts an adaptive scheme to adjust the forgetting factor dynamically and automatically in the online learning process so as to better track the dynamic changes of the time-varying system and reduce the adverse effects of the outdated data in time; thus it tends to provide desirable prediction results in time-varying environment. Detailed performance comparisons of AFGR-OSELM with other representative algorithms are carried out using artificial and real world data sets. The experimental results show that the proposed AFGR-OSELM has higher prediction accuracy with better stability than its counterparts for predicting time-varying system.

No abstract

Sepsis, which is caused by severe infection, is an important cause of mortality, but effective clinical treatment against sepsis is extremely limited. As the main component of the outer membrane of Gram-negative bacteria, lipopolysaccharide (LPS) plays a major role in inflammatory responses. Studies have shown beneficial pharmacological effects for Folium isatidis. The present study further illuminated the effects of n-butanol extract from Folium isatidis in LPS-induced septic shock and identified the main active chemical components. Our study showed that pretreatment with n-butanol extract from Folium isatidis not only significantly inhibited LPS-induced tumor necrosis factor-α and interleukin-6 production but also markedly and dose dependently enhanced the recruitment of MyD88, the phosphorylation of extracellular signal-regulated kinase, and the degradation of IκB-α. Additionally, the extract exhibited dramatic protective effects against lung injury and death in mice with septic shock. Eight main active compounds were identified, including organic acids, glycoside, indolinones, and flavonoids. These findings provide a perspective on the respiratory protection offered by n-butanol extract from Folium isatidis in LPS-induced sepsis and outline a novel therapeutic strategy for the treatment of sepsis.

Deep learning, which is a subfield of machine learning, has opened a new era for the development of neural networks. The auto-encoder is a key component of deep structure, which can be used to realize transfer learning and plays an important role in both unsupervised learning and non-linear feature extraction. By highlighting the contributions and challenges of recent research papers, this work aims to review state-of-the-art auto-encoder algorithms. Firstly, we introduce the basic auto-encoder as well as its basic concept and structure. Secondly, we present a comprehensive summarization of different variants of the auto-encoder. Thirdly, we analyze and study auto-encoders from three different perspectives. We also discuss the relationships between auto-encoders, shallow models and other deep learning models. The auto-encoder and its variants have successfully been applied in a wide range of fields, such as pattern recognition, computer vision, data generation, recommender systems, etc. Then, we focus on the available toolkits for auto-encoders. Finally, this paper summarizes the future trends and challenges in designing and training auto-encoders. We hope that this survey will provide a good reference when using and designing AE models.