The Importance of Expert Knowledge for Automatic Modulation Open Set Recognition.

Automatic modulation classification (AMC) is an important technology for the monitoring, management, and control of communication systems. In recent years, machine learning approaches are becoming popular to improve the effectiveness of AMC for radio signals. However, the automatic modulation open-set recognition (AMOSR) scheme that aims to identify the known modulation types and recognize the unknown modulation signals is not well studied. Therefore, in this paper, we propose a novel multi-modal marginal prototype framework for radio frequency (RF) signals (MMPRF) to improve AMOSR performance. First, MMPRF addresses the problem of simultaneous recognition of closed and open sets by partitioning the feature space in the way of one versus other and marginal restrictions. Second, we exploit the wireless signal domain knowledge to extract a series of signal-related features to enhance the AMOSR capability. In addition, we propose a GAN-based unknown sample generation strategy to allow the model to understand the unknown world. Finally, we conduct extensive experiments on several publicly available radio modulation data, and experimental results show that our proposed MMPRF outperforms the state-of-the-art AMOSR methods.

CLPVG: Circular limited penetrable visibility graph as a new network model for time series.

A visibility graph transforms time series into graphs, facilitating signal processing by advanced graph data mining algorithms. In this paper, based on the classic limited penetrable visibility graph method, we propose a novel mapping method named circular limited penetrable visibility graph, which replaces the linear visibility line in limited penetrable visibility graph with nonlinear visibility arc for pursuing more flexible and reasonable mapping of time series. Tests on degree distribution and some common network features of the generated graphs from typical time series demonstrate that our circular limited penetrable visibility graph can effectively capture the important features of time series and show higher robust classification performance than the traditional limited penetrable visibility graph in the presence of noise. The experiments on real-world time-series datasets of radio and electroencephalogram signals also suggest that the structural features provided by a circular limited penetrable visibility graph, rather than a limited penetrable visibility graph, are more useful for time-series classification, leading to higher accuracy. This classification performance can be further enhanced through structural feature expansion by adopting subgraph networks. All of these results demonstrate the effectiveness of our circular limited penetrable visibility graph model.

Epileptic Seizure Detection with Hybrid Time-Frequency EEG Input: A Deep Learning Approach.

The precise detection of epileptic seizure helps to prevent the serious consequences of seizures. As the electroencephalogram (EEG) reflects the brain activity of patients effectively, it has been widely used in epileptic seizure detection in the past decades. Recently, deep learning-based detection methods which automatically learn features from the EEG signals have attracted much attention. However, with deep learning-based detection methods, different input formats of EEG signals will lead to different detection performances. In this paper, we propose a deep learning-based epileptic seizure detection method with hybrid input formats of EEG signals, i.e., original EEG, Fourier transform of EEG, short-time Fourier transform of EEG, and wavelet transform of EEG. Convolutional neural networks (CNNs) are designed for extracting latent features from these inputs. A feature fusion mechanism is applied to integrate the learned features to generate a more stable syncretic feature for seizure detection. The experimental results show that our proposed hybrid method is effective to improve the seizure detection performance in few-shot scenarios.

Deep Reinforcement Learning Based Decision Making for Complex Jamming Waveforms.

With the development of artificial intelligence, intelligent communication jamming decision making is an important research direction of cognitive electronic warfare. In this paper, we consider a complex intelligent jamming decision scenario in which both communication parties choose to adjust physical layer parameters to avoid jamming in a non-cooperative scenario and the jammer achieves accurate jamming by interacting with the environment. However, when the situation becomes complex and large in number, traditional reinforcement learning suffers from the problems of failure to converge and a high number of interactions, which are fatal and unrealistic in a real warfare environment. To solve this problem, we propose a deep reinforcement learning based and maximum-entropy-based soft actor-critic (SAC) algorithm. In the proposed algorithm, we add an improved Wolpertinger architecture to the original SAC algorithm in order to reduce the number of interactions and improve the accuracy of the algorithm. The results show that the proposed algorithm shows excellent performance in various scenarios of jamming and achieves accurate, fast, and continuous jamming for both sides of the communication.

Do short chain fatty acids and phenolic metabolites of the gut have synergistic anti-inflammatory effects? - New insights from a TNF-α-induced Caco-2 cell model.

Fermentation of dietary fiber and metabolism of polyphenols by the gut microbiota produce short chain fatty acids (SCFAs) and some simple phenolic acids, both of which have been independently shown to have anti-inflammatory effects and to improve gut health. While synergistic interactions between the two colonic metabolite groups have been speculated, direct evidence on whether and how these compounds work together towards collective anti-inflammatory effect and gut health remain unclear. In this study, the most important SCFA butyric acid (BtA) and three phenolic metabolites benzoic acid (BzA), phenylacetic acid (PAA) and phenylpropionic acid (PPA) were selected and assessed for the anti-inflammatory effects and the underlying mechanisms in a TNF-α-induced Caco-2 cell model. Significantly stronger inhibition of TNF-α-induced IL-8 production was found in cells pre-treated with different concentrations of mixtures of BtA and the phenolic metabolites than individual compounds. Further study showed that the synergistic effect was via significant down-regulation of the gene expressions of IL-8, TNF-α and VCAM-1, and of phosphorylation of JNK, p38 and IĸBα, cellular signaling mediators of the MAPK and NF-κB pathways. Although these are results of a cell model, they do provide significant insights into the synergistic anti-inflammatory effects between SCFAs and phenolic metabolites. As both metabolite groups are simultaneously present in the gut, our findings therefore also suggest a potential synergistic effect between the two colonic metabolite groups in maintaining gut health.

Synergistic antioxidant effects of petunidin and lycopene in H9c2 cells submitted to hydrogen peroxide: Role of Akt/Nrf2 pathway.

Phenolics and carotenoids coexist in fruits and vegetables and could possess interaction effects after consumption. The present study aims to elucidate the possible mechanisms of the antioxidant interactions between anthocyanins and carotenoids using petunidin and lycopene as examples in hydrogen peroxide (H2 O2 )-induced heart myofibroblast cell (H9c2) line model. The results revealed that petunidin and lycopene showed antioxidant effects and petunidin in a larger proportion mixed with lycopene, for example, petunidin: lycopene = 9:1 significantly protected against the loss of the cell viability (8.98 ± 1.03%) and intracellular antioxidant enzyme activities of superoxide dismutase (SOD, 27.07 ± 3.51%), catalase (CAT, 29.51 ± 6.12%), and glutathione peroxidase (GSH-Px, 20.33 ± 2.65%). Moreover, the messenger RNA (mRNA) and protein expressions of NAD(P)H quinone reductase (NQO1) and heme oxygenase (HO-1) of the nuclear factor erythrocyte 2-related factor 2 (Nrf2) signaling pathway were significantly induced in petunidin, lycopene, and synergistic combinations, suggesting that the antioxidant action was through activating the Nrf2 antioxidant response pathway. This was further validated by Nrf2 siRNA, and the results that petunidin significantly induced more of NQO1 expression and lycopene more of HO-1 suggested that the synergism may be a result of concerted actions by the two compounds on these two different target genes of the Nrf2 pathway. The two compounds also significantly increased the phosphorylation of Akt in synergistic combinations. Findings of the present study demonstrated that petunidin and lycopene exerted synergistic antioxidant effects when petunidin in a larger proportion in the combinations and contribute to the prevention of cellular redox homeostasis, which might provide a theoretical basis for phenolics and carotenoids playing beneficial effects on the cardiovascular risk. PRACTICAL APPLICATION: In this study, we revealed that the combined treatments of petunidin and lycopen inhibited H2 O2 -induced oxidative damage in myocardial cells. Moreover, the treatments contributed to the Nrf2 pathway and the restoration of cellular redox homeostasis might provide a theoretical basis for phenolics and carotenoids playing beneficial effects on the cardiovascular risk.

The Phenolic Compounds, Metabolites, and Antioxidant Activity of Propolis Extracted by Ultrasound-Assisted Method.

The influences of ultrasound-assisted, pharmacopeia, and supercritical fluid extraction methods on bioactive compounds and biological activities of propolis were evaluated. Results showed that propolis extracted by ultrasound-assisted method contained more phenolic compounds, and showed the highest total phenolic content (245.84 ± 6.41 mg GAE/g DW), total flavonoids content (198.82 ± 5.74 mg RE/g DW), and stronger in vitro antioxidant activity (DPPH·: 1.03 ± 0.04 mmol Trolox/g DW, ABTS+·: 2.19 ± 0.05 mmol Trolox/g DW, and FRAP: 1.48 ± 0.12 mmol FeSO4 /g DW) than those of pharmacopoeia and supercritical fluid methods. A total of 36 phenolic compounds were identified in propolis. Among them, quercetin, quercetin-3-methyl-ether, kaempferol, isorhamnetin, luteolin-methyl-ether, and quercetin-7-methyl-ether could only be found in ultrasound-assisted and pharmacopoeia methods. Moreover, the phenolic compounds had the similar metabolic pathways in rats and were mainly metabolized by sulfation and glucuronidation pathways. Additionally, ultrasonic-treated propolis have good in vivo antioxidant activity and could repair D-galactose-induced oxidative damage in rats. Therefore, ultrasound-assisted method could replace pharmacopeia method to be considered as bioactive compounds extraction from propolis, taking into consideration of yield, short extraction time, and high antioxidant activity.

Daily Dietary Antioxidant Interactions Are Due to Not Only the Quantity but Also the Ratios of Hydrophilic and Lipophilic Phytochemicals.

The hydrophilic extracts of mulberry (HEM) and blueberry (HEB) and lipophilic extracts of mango (LEM) and watermelon (LEW) were mixed in different ratios to assess the antioxidant interactions by chemical-based (DPPH and ABTS assays) and H9c2 cell-based models. There were both synergistic and antagonistic antioxidant interactions among these fruits. Some groups with combinational extracts showed stronger synergistic antioxidant effects than the individual groups, and others (HEM-LEW F1/10, LEW-LEM F5/10, and HEB-LEM F3/10) showed stronger antagonistic effects than the individual groups based on the indicators [the values of DPPH, ABTS, and MTT; the expression of superoxide dismutase (SOD), glutathione peroxidase (GSH-Px), catalase (CAT), and malondialdehyde (MDA); the release of lactate dehydrogenase (LDH); and the quantification of cellular antioxidant activity]. The principal component analysis (PCA) showed that samples could be defined by two principal components: PC1, the main phenolic acids and anthocyanins, and PC2, carotenoids. From our results, primarily, carotenoids were in the majority in antagonistic groups, and phenolics and anthocyanins were in the majority in synergistic groups. However, the combinational groups containing only hydrophilic compounds did not always show synergistic effects. Therefore, the compatibility of diets indicates balancing the ratios of hydrophilic and lipophlic compounds in our daily food. In addition, the expression of enzymes (SOD, GSH-Px, and CAT) may not be sensitive to the changes of antioxidant activity caused by the combinations with different ratios of hydrophilic and lipophilc compounds. The different structures of lipophilic compounds (ß-carotene and lycopene) could influence the antagonistic effects.

Implication of the Significance of Dietary Compatibility: Based on the Antioxidant and Anti-Inflammatory Interactions with Different Ratios of Hydrophilic and Lipophilic Antioxidants among Four Daily Agricultural Crops.

The hydrophilic extracts of eggplant peel (HEEP) and purple sweet potato (HEPP) and lipophilic extracts of tomato (LET) and carrot (LEC) were mixed in different ratios to assess the significance of the compatibility of aliments, based on their antioxidant and anti-inflammatory interactions in H9c2 cells. The results indicated that groups of some combinational extracts (HEPP-HEEP F1/10, LEC-HEEP F3/10, LEC-HEPP F3/10) showed stronger synergistic antioxidant and anti-inflammatory effects than individual groups. For example, the glutathione peroxidase (GPx) activity of the LEC-HEEP (F3/10) group (86.71 ± 1.88) was higher than that in the HEEP (79.97 ± 1.68) and LEC (77.31 ± 1.85) groups. The level of reactive oxygen species (ROS) was 30.37 ± 0.25 in the LEC-HEEP (F3/10) group while the levels were 34.34 ± 0.36 and 46.23 ± 0.51 in the HEEP and LEC groups, respectively. And the level of malondialdehyde (MDA) was 1.82 ± 0.24 in the LEC-HEEP (F3/10) group while the levels were 2.48 ± 0.13 and 3.01 ± 0.24 in the HEEP and LEC groups, respectively. The expressions of inflammatory mediators (IL-1ß, IL-6, IL-8) and cell adhesion molecules (VCAM-1, ICAM-1) showed similar tendencies. However, some groups (LET-LEC F5/10, LET-LEC F9/10, LET-HEPP F7/10) showed antagonistic effects based on these indicators. The principal component analysis showed that samples could be defined by two principal components: PC1, the main phenolic acids and flavonoids; PC2, carotenoids. Moreover, phenolics and anthoyanins were in the majority in synergistic groups, and carotenoids were in the majority in antagonistic groups. These results indicated that there exist synergistic or antagonistic interactions of aliments on antioxidation and anti-inflammation, which implied the significance of food compatibility.

Octyl Ester of Ginsenoside Rh2 Induces Apoptosis and G1 Cell Cycle Arrest in Human HepG2 Cells by Activating the Extrinsic Apoptotic Pathway and Modulating the Akt/p38 MAPK Signaling Pathway.

Ginsenoside Rh2 is a potential active metabolite of ginseng that has antitumor activity against a variety of tumor cells. Previously, we reported that Rh2-O, an octyl ester derivative of ginsenoside Rh2, had a higher anticancer activity than Rh2 through activating the intrinsic apoptotic pathway. In this study, we found that the extrinsic apoptotic pathway was also involved in Rh2-O-induced HepG2 cells apoptosis as evidenced by the up-regulation of Fas, FasL, TNFR1, and TNF-α as well as the cleavage of caspase 8. Moreover, flow cytometric analysis demonstrated that Rh2-O induced G1 cell cycle arrest in HepG2 cells. Rh2-O-induced G1 phase arrest was accompanied by the down-regulation of cyclin D3 and cyclin E and cyclin-dependent kinases (CDK) 4 and 6 and the up-regulation of p21WAF1/CIP1 and p27KIP1. In addition, Rh2-O down-regulated the phosphorylation of Akt, and its inhibitor LY294002 promoted Rh2-O-induced G1 phase arrest. Rh2-O treatment also activated p38 MAPK, JNK, and ERK expression. Inhibitors of p38 MAPK (SB203580), but not those of JNK (SP600125) or ERK (PB98095), promoted Rh2-O-induced G1 phase arrest in HepG2 cells. These results indicated that the disruption of Akt and p38 MAPK cascades played a pivotal role in Rh2-O-induced G1 phase arrest.

Esterification of Ginsenoside Rh2 Enhanced Its Cellular Uptake and Antitumor Activity in Human HepG2 Cells.

Our previous research had indicated that the octyl ester derivative of ginsenoside Rh2 (Rh2-O) might have a higher bioavailability than Rh2 in the Caco-2 cell line. The aim of this study was to investigate the cellular uptake and antitumor effects of Rh2-O in human HepG2 cells as well as its underlying mechanism compared with Rh2. Results showed that Rh2-O exhibited a higher cellular uptake (63.24%) than Rh2 (36.76%) when incubated with HepG2 cells for 24 h. Rh2-O possessed a dose- and time-dependent inhibitory effect against the proliferation of HepG2 cells. The IC50 value of Rh2-O for inhibition of HepG2 cell proliferation was 20.15 µM, which was roughly half the value of Rh2. Rh2-O induced apoptosis of HepG2 cells through a mitochondrial-mediated intrinsic pathway. In addition, the accumulation of ROS was detected in Rh2-O-treated HepG2 cells, which participated in the apoptosis of HepG2 cells. Conclusively, the findings above all suggested that Rh2-O as well as Rh2 inducing HepG2 cells apoptosis might involve similar mechanisms; however, Rh2-O had better antitumor activities than Rh2, probably due to its higher cellular uptake.