Search

Emotion recognition plays an important role in Human Computer Interaction (HCI) and the evaluation of human behavior based on emotional state is an important research topic. The purpose of emotion recognition is to automatically identify human’s emotional states by analyzing physiological or non-physiological signals. The conventional emotion classification methods cannot comprehensively leverage global and local features which are extracted from Electroencephalogram (EEG) signal generated after being stimulated. Therefore, we propose the graph convolutional neural network based emotion recognition with brain functional connectivity network (GERBN). Firstly, raw EEG data of the public DEAP and SEED datasets is preprocessed and adopted in this study. Secondly, emotion-related brain functional connection pattern is constructed using Phase-Locking Value (PLV) adjacency matrix to measure connectivity between the signals of different EEG channels according to phase synchronization. A novel graph structure is constructed where the EEG electrode channels are defined as the vertex, and the edge is strong connection of the binary brain network. Thirdly, the GERBN model that includes six layers is designed to classify and recognize emotional states on the two-dimensional emotional models of valence and arousal. Finally, extensive experiments are conducted on DEAP and SEED datasets. Experimental results demonstrate that the proposed method can improve classification accuracies, in which average accuracies of 80.43% and 88.47% on DEAP are attained on valence and arousal dimensions, respectively. On the SEED dataset, the accuracy reaches 92.37% higher than some of the other methods.

Probe-based confocal laser endomicroscopy (pCLE) is a significant diagnostic instrument and is frequently utilized to diagnose the severity of gastric intestinal metaplasia (GIM). The physicians must comprehensively analyze video clips recorded with pCLE from the gastric antrum, gastric body, and gastric angle area to determine the patient’s condition. However, due to the limitations of the pCLE’s microscopic imaging structure, the gastric areas detected cannot be identified and recorded in real time, which may poses a risk of missing potential areas of disease occurrence and is not conducive to the subsequent precise treatment of the lesion area. Therefore, this paper proposes an endoscopic video aided identification method for identifying gastric areas (EVIGA), which are utilized for determining the detected areas of pCLE in real-time. Firstly, the start time of the diagnosis clip is determined by real-time detecting the working states of pCLE. Then, the endoscopic video clip is truncated according to the correspondence between pCLE and endoscopic video in the time sequence for detecting gastric areas. In order to accurately identify pCLE detected gastric areas, a probe-based confocal laser endomicroscopy diagnosis area identification model (pCLEDAM) is constructed with an hourglass convolution designed for single-frame feature extraction and a temporal feature-sensitive extraction structure for spatial feature extraction. The extracted feature maps are unfolded and fed into the fully connected layer to classify the detected areas. To validate the proposed method, 67 clinical confocal laser endomicroscopy diagnosis cases are collected from a tertiary care hospital, and 500 video clips are finally reserved after audited for dataset construction. Experiments show that the accuracy of area identification on the test dataset achieves 96.0% and is much higher than other related algorithms, achieving the accurate identification of pCLE detected areas.

During a hospital visit, a significant volume of Gastroscopy Diagnostic Text (GDT) data are produced, representing the unstructured gastric medical records of patients undergoing gastroscopy. As such, GDTs play a crucial role in evaluating the patient’s health, shaping treatment plans, and scheduling follow-up visits. However, given the free-text nature of GDTs, which lack a formal structure, physicians often find it challenging to extract meaningful insights from them. Furthermore, while deep learning has made significant strides in the medical domain, to our knowledge, there are not any readily available text-based pre-trained models tailored for GDT classification and analysis. To address this gap, we introduce a Bidirectional Encoder Representations from Transformers (BERT) based three-branch classification network tailored for GDTs. We leverage the robust representation capabilities of the BERT pre-trained model to deeply encode the texts. A unique three-branch decoder structure is employed to pinpoint lesion sites and determine cancer stages. Experimental outcomes validate the efficacy of our approach in GDT classification, with a precision of 0.993 and a recall of 0.784 in the early cancer category. In pinpointing cancer lesion sites, the weighted F1 score achieved was 0.849.

Major depressive disorder (MDD) is the most common psychological disease. To improve the recognition accuracy of MDD, more and more machine learning methods have been proposed to mining EEG features, i.e. typical brain functional patterns and recognition methods that are closely related to depression using resting EEG signals. Most existing methods typically utilize threshold methods to filter weak connections in the brain functional connectivity network (BFCN) and construct quantitative statistical features of brain function to measure the BFCN. However, these thresholds may excessively remove weak connections with functional relevance, which is not conducive to discovering potential hidden patterns in weak connections. In addition, statistical features cannot describe the topological structure features and information network propagation patterns of the brain’s different functional regions. To solve these problems, we propose a novel MDD recognition method based on a multi-granularity graph convolution network (MGGCN). On the one hand, this method applies multiple sets of different thresholds to build a multi-granularity functional neural network, which can remove noise while fully retaining valuable weak connections. On the other hand, this method utilizes graph neural network to learn the topological structure features and brain saliency patterns of changes between brain functional regions on the multi-granularity functional neural network. Experimental results on the benchmark datasets validate the superior performance and time complexity of MGGCN. The analysis shows that as the granularity increases, the connectivity defects in the right frontal(RF) and right temporal (RT) regions, left temporal(LT) and left posterior(LP) regions increase. The brain functional connections in these regions can serve as potential biomarkers for MDD recognition.

Network virtualization can effectively establish dedicated virtual networks to implement various network functions. However, the existing research works have some shortcomings, for example, although computing resource properties of individual nodes are considered, node storage properties and the network topology properties are usually ignored in Virtual Network (VN) modelling, which leads to the inaccurate measurement of node availability and priority. In addition, most static virtual network mapping methods allocate fixed resources to users during the entire life cycle, and the users’ actual resource requirements vary with the workload, which results in resource allocation redundancy. Based on the above analysis, in this paper, we propose a dynamic resource sharing virtual network mapping algorithm named NMA-PRS-VNE, first, we construct a new, more realistic network framework in which the properties of nodes include computing resources, storage resources and topology properties. In the node mapping process, three properties of the node are used to measure its mapping ability. Second, we consider the resources of adjacent nodes and links instead of the traditional method of measuring the availability and priority of nodes by considering only the resource properties, so as to more accurately select the physical mapping nodes that meet the constraints and conditions and improve the success rate of subsequent link mapping. Finally, we divide the resource requirements of Virtual Network Requests (VNRs) into basic sub-requirements and variable sub-variable requirements to complete dynamic resource allocation. The former represents monopolizing resource requirements by the VNRs, while the latter represents shared resources by many VNRs with the probability of occupying resources, where we keep a balance between resource sharing and collision among users by calculating the collision probability. Simulation results show that the proposed NMA-PRS-VNE can increase the average acceptance rate and network revenue by 15% and 38%, and reduce the network cost and link pressure by 25% and 17%.

Time series classification exists in widespread domains such as EEG/ECG classification, device anomaly detection, and speaker authentication. Although many methods have been proposed, efficient selection of intuitive temporal features to accurately classify time series remains challenging. Therefore, this paper presents TSC-RTF, a new time series classification method using random temporal features. First, to ensure the intuitiveness of the features, TSC-RTF selects subsequences containing important data points as candidates for intuitive temporal features. Then, TSC-RTF uses random sampling to reduce the number of candidates significantly. Next, TSC-RTF selects the final temporal features using a random forest to ensure the validity of the final temporal features. Finally, a deep learning classifier is trained by TSC-RTF to achieve high accuracy. The experimental results show that the proposed method can compete with the state-of-the-art methods.

Abstract Background As known, inhibition of phosphodiesterase 5 (PDE5) has the therapeutic effect on male erectile dysfunction (ED), and the processed folium of Epimedium sagittatum Maxim. (PFES) characterized by 8-isopentenyl flavonoids is a famous herb for treating ED. However, the main flavonoids inhibitory activities, structure–activity relationship (SAR) and signaling pathway have been not systematically studied so that its pharmacodynamic mechanism is unclear. Methods We aimed to initially reveal the PFES efficacy mechanism for treating ED. For the first time, 6 main 8-isopentenyl flavonoids (1–6) from PFES were isolated and identified. Then based on HPLC detection, we proposed a novel method to screen inhibitors among them. We further analyze the three-dimensional quantitative structure–activity relationship (3D-QSAR) for those inhibitors. Results The results were verified by cellular effects of the screened flavonoids. Among 6 compounds, Icariin: (1), 2-Oʹʹrhamnosylicaridide II (2) and Baohuoside I (3) were identified with significant activities (IC50 = 8.275, 3.233, 5.473 μM). Then 3D-QSAR studies showed that the replacement of C8 with bulky steric groups as isopentenyl, C3 with positive charge groups and C4' with a hydrogen bond acceptor substituent could increase inhibitory effects. In contrast, the substitution of C7 with bulky steric groups or hydrophilic groups tended to decrease the efficacies. And compounds 1, 2, 3 could increase cGMP level and decrease cytoplasmic Ca2+ of rat corpus cavernosum smooth muscle cells (CCSMCs)by activating PKG. Conclusion 8-isopentenyl flavonoids could be the main pharmacodynamic substances of PFES in the treatment for ED, and some had significant PDE5A1 inhibitory activities so as to activate cGMP/PKG/Ca2+ signaling pathway in CCSMCs, that was related to the substituents at the key sites such as C8, C3, C4ʹ and C7 in the characteristic compounds.

Electronic Health Records (EHRs) contain unprecedented volumes of data related to health such as diagnosis and treatment information. Based on the technologies of named entity recognition (NER), EHRs mining has become a research focus in health domain. Nevertheless, the complex medical entities are challenging to be recognized, especially in Chinese EHRs. In this paper, a Glyph and Word Boundary-based Named Entity Recognition (GWBNER) method is presented, which takes into account both the Chinese character glyph and word boundary features in Chinese EHRs. Specifically, the character glyphs are utilized to capture the character-level global structural features, and the word boundaries are adopted to extract the word-level local structural features in Chinese. Therefore, the medical entities are fully recognized with rich semantic features from diverse perspectives in Chinese EHR texts. Finally, we conduct extensive experiments to evaluate the novel approach, and the F1 scores of 0.879, 0.998 and 0.962 are achieved on three EHR datasets, respectively. The experimental results demonstrate the optimal performance of the GWBNER method compared with the state-of-the-art models in NER community.

Background: Kidney-Yang deficiency syndrome (KDS) is a group of diseases related to hypothalamic-pituitary-adrenal (HPA) axis and sexual dysfunction. The folium of Epimedium brevicornu Maxim. (FEB) includes raw and prepared slices, named RFEB and PFEB, respectively. PFEB is traditionally believed to be good for tonifying kidney-Yang and improving sexual dysfunction. However, there are few studies comparing the pharmacological effects of RFEB and PFEB, and their underlying mechanisms. In this study, we aimed to compare the effects and safety of RFEB and PFEB on the HPA axis and sexual function. Additionally, the mechanisms of their roles in relation to the neuroendocrine-immune (NEI) network in the KDS model mice were explored.Methods: Male adult C57BL/6 mice were treated with corticosterone to establish a KDS mouse model, and RFEB and PFEB were administered intragastrically. Corticotropin releasing hormone (CRH), adrenocorticotropic hormone (ACTH), cyclic adenosine monophosphate (cAMP), cyclic guanosine monophosphate (cGMP), testosterone levels and oxidative damage indexes were measured. The mRNA and protein levels of CRH and ACTH in hypothalamus and pituitary, endothelial nitric oxide synthase (eNOS) and phosphodiesterase 5 (PDE5) in corpus cavernosum were examined. TNFα, IL-6, NF-κB, eNOS and PDE5 were investigated in mouse corpus cavernosum.Results: Our results showed that PFEB was more effective than RFEB in increasing corticosterone-suppressed ACTH levels, enhancing CRH levels and cAMP/cGMP ratio, and reducing oxidative damage. In vivo, PFEB significantly increased eNOS and inhibited PDE5 expression in corpus cavernosum. PFEB showed stronger protective effect on normal spleen lymphocytes from apoptosis both in vitro and in vivo. Additionally, it noticeably inhibited the levels of inflammatory cytokines in corpus cavernosum. Both RFEB and PFEB were safe and did not cause any clinical signs of toxicity in mice at the dosage of 20 times dosages of that in the Chinese Pharmacopeia.Conclusion: We demonstrated that PFEB was better than RFEB at tonifying the kidney-Yang by comparing their effects on improving the NEI network, which includes the HPA axis, immune system and corpus cavernosum. This study revealed that PFEB could significantly improve the sexual function of KDS mice by regulating the HPA axis and activating the immune system through the NEI network.

Since multimodal emotion classification in different human states has rarely been studied, this paper explores the emotional mechanisms of the brain functional connectivity networks after emotional stimulation. We devise a multimodal emotion classification method fusing a brain functional connectivity network based on electroencephalography (EEG) and eye gaze (ECFCEG) to study emotional mechanisms. First, the nonlinear phase lag index (PLI) and phase-locked value (PLV) are calculated to construct the multiband brain functional connectivity networks, which are then converted into binary brain networks, and the seven features of the binary brain networks are extracted. At the same time, the features of the eye gaze signals are extracted. Then, a fusion algorithm called kernel canonical correlation analysis, based on feature level and randomization (FRKCCA), is executed for feature-level fusion (FLF) of brain functional connectivity networks and eye gaze. Finally, support vector machines (SVMs) are utilized to classify positive and negative emotions in multiple frequency bands with single modal features and multimodal features. The experimental results demonstrate that multimodal complementary representation properties can effectively improve the accuracy of emotion classification, achieving a classification accuracy of 91.32±1.81%. The classification accuracy of pupil diameter in the valence dimension is higher than that of additional features. In addition, the average emotion classification effect of the valence dimension is preferable to that of arousal. Our findings demonstrate that the brain functional connectivity networks of the right brain exhibit a deficiency. In particular, the information processing ability of the right temporal (RT) and right posterior (RP) regions is weak in the low frequency after emotional stimulation; Conversely, phase synchronization of the brain functional connectivity networks based on PLI is stronger than that of PLV.

The diterpenoid fraction (DF) prepared from fruit of Rhododendron molle was shown to have potential therapeutic effects on collagen-induced arthritis (CIA) rats based on our previous studies. As a continuation of those studies, herein, a lipopolysaccharide-induced endotoxin shock mouse model was used. The results showed that 0.2 mg/ml of DF significantly increased the mouse survival rate and had an anti-inflammatory effect. Further studies showed that DF could decrease the proportion of T helper cells (Th1 and Th17), and increase the proportion of Th2 and regulatory T cells (Tregs). Enzyme-linked immunosorbent assays indicated that DF inhibited the secretion of inflammatory cytokines such as TNF-α, IL-1β, and IL-6; western blotting showed that DF significantly reduced the levels of phosphorylated STAT1 and STAT3. In vitro, DF could dose-dependently inhibit the polarization of naive CD4+ T cells to Th1 or Th17 cells. DF at 10 μg/ml could markedly decrease the expression of mRNA encoding IFN-γ and T-bet, and suppress Th1 differentiation by downregulation of the activity of STAT1 and STAT4. Meanwhile, DF at 10 μg/ml remarkably reduced the expression of mRNA encoding IL-17a, IL-17f, and RORγt, and downregulated STAT3 phosphorylation, suggesting that DF could inhibit Th17 differentiation by reducing STAT3 activation. Taken together, DF blocked the JAK/STAT signaling pathway by inhibiting STAT1 and STAT3 phosphorylation, which clarified the important role of JAK/STAT signaling pathway in anti-rheumatoid arthritis.

Electroencephalogram (EEG) has been widely utilized in emotion recognition. Psychologists have found that emotions can be divided into conscious emotion and unconscious emotion. In this article, we explore to classify subliminal emotions (happiness and anger) with EEG signals elicited by subliminal face stimulation, that is to select appropriate features to classify subliminal emotions. First, multi-scale sample entropy (MSpEn), wavelet packet energy (Ei), and wavelet packet entropy (WpEn) of EEG signals are extracted. Then, these features are fed into the decision tree and improved random forest, respectively. The classification accuracy with Ei and WpEn is higher than MSpEn, which shows that Ei and WpEn can be used as effective features to classify subliminal emotions. We compared the classification results of different features combined with the decision tree algorithm and the improved random forest algorithm. The experimental results indicate that the improved random forest algorithm attains the best classification accuracy for subliminal emotions. Finally, subliminal emotions and physiological proof of subliminal affective priming effect are discussed.

Elderly people are more likely to experience myocardial infarction (MI) than young people, with worse post-MI mortality and prognosis. Ginkgo biloba extract 50 (GBE50) is an oral GBE product that matches the German product, EGb761, which has been used to treat acute myocardial infarction (AMI). The extraction purity of GBE50 was improved to form a new formulation, Ginkgo biloba extract 80 (GBE80). This study investigates the effect of GBE80 on aged acute myocardial infarction rats. GBE80 injection is a novel formulation that was prepared by mixing Ginkgo flavonoids and lactones in a 4:1 weight ratio, with a Ginkgo content of more than 80%. Cell Counting Kit-8 was used to determine the biological safety and protective effect of GBE80 on cardiomyocytes against oxidative damage. An aged AMI rat model was developed and used to determine the myocardial infarction weight ratio using triphenyltetrazolium chloride staining. Terminal deoxynucleotidyl transferase-mediated dUTP-biotin nick end labeling (TUNEL) was applied to detect cell apoptosis in myocardial tissue. Western blotting and immunohistochemistry were used to measure the protein levels of members of the AKT/GSK3β/β-catenin pathway in vitro and in vivo, respectively. We found that GBE80 in vitro suppressed H2O2-induced cytotoxicity by promoting AKT/GSK3β/β-catenin signaling, while it did not show cytotoxicity to normal cardiomyocytes in the 0–500 μg/ml dose range. After 7 days of administration to aged AMI rats, GBE80 markedly reduced the weight ratio of the infarction and inhibited cell apoptosis in myocardial tissue. Furthermore, the AKT/GSK3β/β-catenin signaling pathway was activated by GBE80. These results suggest that GBE80 injection effectively inhibited AMI-induced myocardial damage and in vitro H2O2-induced cardiomyocyte cytotoxicity by activating the AKT/GSK3β/β-catenin signaling pathway.

The study of crowd movement has recently become a popular research topic due to the increasing frequency of public safety issues. Compared with human evacuation experiments and drills, which may have personal safety risks and require a large number of volunteers, a simple and convenient computer simulation has become the mainstream research method. The computer simulation first needs to characterize small groups in the crowd to model the motion state of crowds for more accurate crowd modeling. In this paper, a top-bottom hierarchical clustering algorithm based on off-line crowd trajectories is proposed to provide small group information for crowd motion simulation. First, an unmanned aerial vehicle and a tracking technology are used to capture the pedestrian flow and extract the pedestrian trajectory. Second, a top-bottom hierarchical clustering strategy is proposed to divide the crowd into groups, which solves the problem of the difficulty of ascertaining small groups. This method solves the problem of automatically determining cluster centers by using the improved density peak clustering algorithm combined with a greedy algorithm. One factor of distinguishing small groups is improved by replacing the angle of the direction of motion with the distance difference, thus reducing the computational complexity. Specifically, the mean distance between trajectories based on the Euclidean distance is used for the top-level coarse-grained clustering; then, the improved Hausdorff mean distance is determined in the bottom-level fine-grained clustering. Third, the proposed algorithm is validated by classifying the groups of pedestrians in real videos. The experiments show that the proposed method is applicable and effective.

With the development of information technology, various data-driven intelligent services have changed our daily life greatly. As the data fuels the development of these services, data sharing is desirable for data availability issues. Many mechanisms and technologies have been proposed to support data sharing. However, some organizations, especially with potential competitive relationships are still reluctant to share their data. On one hand, no data holder wish to see the competitiveness improvement of competitors by data sharing. On the other hand, data sharing suffers from huge privacy security risks. To encourage data sharing, in this paper, a competitiveness-driven and secure incentive mechanism is proposed. By introducing the concept of data competitiveness as incentive motivation, competitiveness worry of data holders is eliminated. Privacy is protected by adopting differential privacy. As the privacy protection levels of data holders are unknown to the data demander, a contract theoretic approach is proposed to formulate the incentive mechanism. With the design of optimal contracts, the data demander can make the best decisions to pay data holders and data holders can optimize their utilities by choosing proper contracts. The numerical results demonstrate the effectiveness of the proposed incentive scheme.

Depression has become a serious disease that affects people’s mental health. How to detect it promptly and accurately is a difficult task. Electroencephalogram can reflect the spontaneous biological potential signals in the cerebral cortex and is widely used in the prediction and diagnosis of depression. With electroencephalogram, the key and most difficult challenge is to find the brain regions and frequencies associated with depression, especially mild depression. At present, the most commonly used method is the combination of feature selection and classification algorithm for detection. However, the classification accuracy needs to be further improved. The differential evolution is a population-based adaptive global optimization algorithm. Due to its fast convergence and strong robustness, this paper uses it to optimize the extracted features to achieve better result. Then the k-nearest neighbor classification algorithm is used to classify patients with mild depression and normal people. The experiment is performed on a data set of 10 subjects with mild depression and 10 normal subjects. The results show that the method can find the relatively optimal features and distinguish the two groups of subjects better. It effectively improves the classification accuracy and efficiency, and is superior to other feature optimization methods.

Background and Objective. Qingke (Tibetan hulless barley, Hordeum vulgare L.) contains a high content of β-glucan among all the cereal varieties. Although β-glucan has multiple physiological functions, the physiological function of qingke β-glucan was few studied. In this study, the β-glucan was isolated, purified, determined the structural characterization, and measured the inhibitory activity to enzymes correlating blood sugar and lipid. Methods. β-Glucan was isolated from enzymatic aqueous extract of qingke by using deproteinization, decolorization, DEAE-52 column chromatography, and sepharose CL-4B agarose gel column chromatography. The structure of the β-glucan was determined using FT-IR and 13C-NMR spectra analysis, and molecular mass by use of HPSEC-dRI-LS. The kinematic viscosity was measured. The inhibitory effects of this β-glucan on four enzymes were investigated. Results. This β-glucan had a uniform molecular weight of 201,000 Da with β-(1⟶4) as the main chain and β-(1⟶3) as a side chain. The β-glucan presented a relatively strong inhibitory activity on α-glucosidase, moderate inhibition on invertase, and a weak inhibition on α-amylase, whereas it did not inhibit lipase. Conclusion. The study indicates that the enzymatic β-glucan from qingke has the potential as natural auxiliary hypoglycemic additives in functional medicine or foods.

Sleep-related diseases seriously affect the life quality of patients. Sleep stage classification (or sleep staging), which studies the human sleep process and classifies the sleep stages, is an important reference to the diagnosis and study of sleep disorders. Many scholars have conducted a series of sleep staging studies, but the correlation between different sleep stages and the accuracy of classification still needs to be improved. Therefore, this paper proposes an automatic sleep stage classification based on EEG. By constructing an improved empirical mode decomposition and K-means experimental model, the concept of “frequency-domain correlation coefficient” is defined. In the process of feature extraction, the feature vector with the best correlation in the time-frequency domain is selected. Extraction and classification of EEG features are realized based on the K-means clustering algorithm. Experimental results demonstrate that the classification accuracy is significantly improved, and our proposed algorithm has a positive impact on sleep staging compared with other algorithms.

In the era of big data and artificial intelligence, data sharing is desirable for vigorous development of data-driven services, which improves our daily life. Although data sharing is supported to a certain extent by current mechanisms and technologies, organizations especially with potential competitive relationships might refuse to share their data due to the worry that data sharing improves competitors’ competitiveness. To address this problem, this paper focuses on the competitiveness-driven target of win-win, and provides incentives to encourage potentially competing organizations to share their data. By introducing the concept of data competitiveness as a data transaction driving force, an incentive mechanism based on data competitiveness is established, which is formulated as a Stackelberg game. A gradient-based iteration algorithm is proposed to obtain the Stackelberg equilibrium solution to the data sharing incentive problem. Simulation results substantiate that performance of data sharing can be improved significantly by the proposed scheme.

In this paper, a new color watermarking algorithm based on differential evolution is proposed. A color host image is first converted from RGB space to YIQ space, which is more suitable for the human visual system. Then, apply three-level discrete wavelet transformation to luminance component Y and generate four different frequency sub-bands. After that, perform singular value decomposition on these sub-bands. In the watermark embedding process, apply discrete wavelet transformation to a watermark image after the scrambling encryption processing. Our new algorithm uses differential evolution algorithm with adaptive optimization to choose the right scaling factors. Experimental results show that the proposed algorithm has a better performance in terms of invisibility and robustness.

Sleep stage classification plays an important role in the diagnosis of sleep-related diseases. However, traditional automatic sleep stage classification is quite challenging because of the complexity associated with the establishment of mathematical models and the extraction of handcrafted features. In addition, the rapid fluctuations between sleep stages often result in blurry feature extraction, which might lead to an inaccurate assessment of electroencephalography (EEG) sleep stages. Hence, we propose an automatic sleep stage classification method based on a convolutional neural network (CNN) combined with the fine-grained segment in multiscale entropy. First, we define every 30 seconds of the multichannel EEG signal as a segment. Then, we construct an input time series based on the fine-grained segments, which means that the posterior and current segments are reorganized as an input containing several segments and the size of the time series is decided based on the scale chosen depending on the fine-grained segments. Next, each segment in this series is individually put into the designed CNN and feature maps are obtained after two blocks of convolution and max-pooling as well as a full-connected operation. Finally, the results from the full-connected layer of each segment in the input time sequence are put into the softmax classifier together to get a single most likely sleep stage. On a public dataset called ISRUC-Sleep, the average accuracy of our proposed method is 92.2%. Moreover, it yields an accuracy of 90%, 86%, 93%, 97%, and 90% for stage W, stage N1, stage N2, stage N3, and stage REM, respectively. Comparative analysis of performance suggests that the proposed method is better, as opposed to that of several state-of-the-art ones. The sleep stage classification methods based on CNN and the fine-grained segments really improve a key step in the study of sleep disorders and expedite sleep research.

The aim of this study was to identify bioactive compounds from leaves of the invasive plant Xanthium spinosum and assess their phytotoxic activity. Activity-guided fractionation led to the isolation of 6 bioactive compounds: xanthatin (1), 1α,5α-epoxyxanthatin (2), 4-epiisoxanthanol (3), 4-epixanthanol (4), loliolide (5) and dehydrovomifoliol (6). Of them, compounds 2⁻6 were isolated from the X. spinosum for the first time. The structures of 1⁻6 were elucidated on the basis of extensive NMR studies and ESI-MS measurements as well as comparison with literature data. All of compounds were evaluated for their phytotoxic activity. Among them, compounds 1⁻4 exhibited stronger activity on 2 receiver plants compared with the other 2 compounds, with xanthatin (1) being the most potent compound, which suppressed root growth of the dicot plant Amaranthus retroflexus by 32.5%, 39.4%, 84.7% when treated xanthatin (1) at 5, 20, and 100 µg/mL, while for the monocot plant, root growth was inhibited by 14.7%, 28.0%, and 40.0%, respectively. Seedling growth was nearly completely inhibited when the concentration of xanthanolides increased to 500 µg/mL, whereas there was still some seedling growth when loliolide (5) and dehydrovomifoliol (6) were applied at the same concentration. Dehydrovomifoliol (6) did not negatively affect seedling growth of P. annua at all tested concentrations, and root length was still 42.0% of the control when the highest concentration 500 µg/mL was used. This is the first report of the phytotoxicity of 1α,5α-epoxyxanthatin (2), 4-epiisxanthanol (3) and 4-epixanthanol (4). These compounds have the potential to be utilized as natural herbicides, especially 4-epiisoxanthanol (3), which exhibited significant selective activity between the dicot and monocot plants. On the other hand, whether these bioactive substances serve as allelochemicals to facilitate the invasion success of X. spinosum needs to be further studied.

Multi-Objective Particle Swarm Optimizers (MOPSOs) are easily trapped in local optima, cost more function evaluations and suffer from the curse of dimensionality. A scalable cooperative coevolution and ?-dominance based MOPSO (CEPSO) is proposed to address these issues. In CEPSO, Multi-objective Optimization Problems (MOPs) are decomposed in terms of their decision variables and are optimized by cooperative coevolutionary subswarms, and a uniform distribution mutation operator is adopted to avoid premature convergence. All subswarms share an external archive based on ?-dominance, which is also used as a leader set. Collaborators are selected from the archive and used to construct context vectors in order to evaluate particles in a subswarm. CEPSO is tested on several classical MOP benchmark functions and experimental results show that CEPSO can readily escape from local optima and optimize both low and high dimensional problems, but the number of function evaluations only increases linearly with respect to the number of decision variables. Therefore, CEPSO is competitive in solving various MOPs.