With everyday advances in the field of pharmaceuticals, medicinal plants have high priority regarding the introduction of novel synthetic compounds by the usage of environmentally friendly extraction technologies. Herein, a supercritical CO2 extraction method was implemented in the analysis of four plants (chamomile, St. John’s wort, yarrow, and curry plant) after which the non-targeted analysis of the chemical composition, phenolic content, and antioxidant activity was evaluated. The extraction yield was the highest for the chamomile (5%), while moderate yields were obtained for the other three plants. The chemical composition analyzed by gas chromatography-high-resolution mass spectrometry (GC-HRMS) and liquid chromatography-high-resolution mass spectrometry (LC-HRMS) demonstrated extraction of diverse compounds including terpenes and terpenoids, fatty acids, flavonoids and coumarins, functionalized phytosterols, and polyphenols. Voltammetry of microfilm immobilized on a glassy carbon electrode using square-wave voltammetry (SWV) was applied in the analysis of extracts. It was found that antioxidant activity obtained by SWV correlates well to 1,1-diphenyl-2-picrylhidrazine (DPPH) radical assay (R2 = 0.818) and ferric reducing antioxidant power (FRAP) assay (R2 = 0.640), but not to the total phenolic content (R2 = 0.092). Effective results were obtained in terms of activity showing the potential usage of supercritical CO2 extraction to acquire bioactive compounds of interest.

Abstract This paper seeks to empirically explore how an international financial integration influences a country’s GDP growth. The long run relationship is tested by PMG estimator for the sample of ten EU countries from Central, Eastern and Southeastern Europe (CEE-10 countries) between 1995 and 2017. Prior to the conducting of dynamic panel analysis based on PMG estimators, several panel unit root tests were conducted, as well as panel co integration tests. The findings offer mixed impact financial integration on growth. Among the measures of financial integration, growth of the CEE-10 countries is mostly driven in the long run by FDI inflows as well as remittances and financial openness. On the contrary, the study suggests a reversal relationship between growth and financial integration measured by Gross Foreign Assets and Liabilities in percentages of GDP. It might be explained with a fact that CEE-10 countries have not yet reached a certain level of financial development in order to benefit from financial integration. The study concludes that international financial integration does not per se enhance economic growth and country’s growth in the CEE-10 countries can be reached at a higher level of financial integration, further increase their financial openness and financial development.

In this paper, we propose Federated Deep Learning (FDL) for intrusion detection in heterogeneous networks. Local Deep Neural Network (DNN) models are used to learn the hierarchical representations of the private network traffic data in multiple edge nodes. A dedicated central server receives the parameters of the local DNN models from the edge nodes, and it aggregates them to produce an FDL model using the Fed+ fusion algorithm. Simulation results show that the FDL model achieved an accuracy of 99.27 ± 0.79%, a precision of 97.03 ± 4.22%, a recall of 98.06 ± 1.72%, an F1 score of 97.50 ± 2.55%, and a False Positive Rate (FPR) of 2.40 ± 2.47%. The classification performance and the generalisation ability of the FDL model are better than those of the local DNN models. The Fed+ algorithm outperformed two state-of-the-art fusion algorithms, namely federated averaging (FedAvg) and Coordinate Median (CM). Therefore, the DNN-Fed+ model is preferable for intrusion detection in heterogeneous wireless networks.

Malware traffic classification (MTC) is a key technology for solving anomaly detection and intrusion detection problems. And hence it plays an important role in the field of network security. Traditional MTC methods based on port, payload and statistic depend on the manual-designed features, which have low accuracy. Recently, deep learning methods have attracted significant attention due to their high accuracy in terms of classification. However, in practical application scenarios, deep learning methods require a large amount of labeled samples for training, while the available labeled samples for training are very rare. Furthermore, the preparation of a large amount of labeled samples requires a lot of labor costs. To solve these problems, this paper proposes two methods based on semi-supervised learning (SSL) and transfer learning (TL), respectively. Our proposed methods use a large amount of unlabeled data collected in the Internet traffic, which can greatly improve the accuracy classification with few labeled samples. Through experiments, we obtained the best method to improve the accuracy of few labeled samples in different situations. Experiment results show that our proposed methods can satisfy the requirement of MTC in the case of few labeled samples.

Intelligent reflecting surface (IRS)-aided millimeter-wave (mmWave) multiple-input single-output (MISO) is considered one of the promising techniques in next-generation wireless communication. However, existing beamforming methods for IRS-aided mm Wave MISO systems require high computational power, so it cannot be widely used. In this paper, we combine an unsupervised learning-based fast beamforming method with IRS-aided MISO systems, to significantly reduce the computational complexity of this system. Specifically, a new beamforming design method is proposed by adopting the feature fusion means in unsupervised learning. By designing a specific loss function, the beamforming can be obtained to make the spectrum more efficient, and the complexity is lower than that of the existing algorithms. Simulation results show that the proposed beamforming method can effectively reduce the computational complexity while obtaining relatively good performance results.

Accurate downlink channel state information (CSI) is one of the essential requirements for harnessing the potential advantages of frequency-division duplexing (FDD) massive multi-input multi-output (MIMO) systems. The current state-of-art in this vibrant research area include the use of deep learning to compress and feedback downlink CSI at the user equipments (UEs). These approaches focus mainly on achieving CSI feedback with high reconstruction performance and low complexity, but at the expense of inflexible compression rate (CR). High training overheads and limited storage capacity requirements are some of the challenges associated with the design of dynamic CR, which instantaneously adapt to propagation environment. This paper applies transfer learning (TL) to develop a multi-rate CSI compression and recovery neural network (TL-MRNet) with reduced training overheads. Simulation results are presented to validate the superiority of the proposed TL-MRNet over traditional methods in terms of normalized mean square error and cosine similarity.

The inception of artificial intelligence (AI) dates back to the 1950s, with the latest wave of AI featuring unprecedented “machine learning” capabilities, including “deep learning.” With these increased capacities, AI is disrupting society in both beneficial and disempowering ways, exemplified in medical and scientific advances and enabling oppressive surveillance [1]. The rate of adoption and potential of this wave of AI are novel, as are the socio-technical problems developing with emerging technologies powered by AI.

Abstract Polycyclic aromatic hydrocarbons (PAHs) are formed from anthropogenic activities, i.e. industrial emissions, incomplete combustion of petroleum, coal and other fossil fuels and other industrial and domestic activities. Research areas of this study are four representative locations in the industrial complex, in the city of Banja Luka, Republic of Srpska, Bosnia and Herzegovina. The main objective of the paper is to determine the ecological risk and to assess probable sources of PAHs contamination in soil and groundwater. The results of this study reflect the effects of coal combustion (pyrogenic origin), petrogenic and biomass origin and may provide basic data for the remediation of PAHs in the location. The ecological risk in soil (at depths of 30, 100, 200, 300 and 400 cm) and groundwater is determined. The mean values of ecological risk in soil and groundwater decreased with soil depth. Values of RQ(NCs) for groundwater were found at high ecological risk, for Ant, Chr, DahA, Acy, Pyr, BaA, Phe, Flo, Nap, Ace and Fluo, with values 28.57, 20.59, 300.00, 242.86, 185.71, 1700.0, 76.67, 53.33, 15.83, 100.00 and 57.14, respectively. ∑16PAH indicated high ecological risk for most PAHs, which decreased with soil depth. The value of RQ(NCs) for ΣPAHs in groundwater indicates high ecological risk (ΣPAHs ≥ 800 and RQ(MPCs) ≥ 1). This is the first study on the ecological risk of PAHs in soil and groundwater in industrial soils in Banja Luka and provides baseline information for further studies and additional investigations of this industrial complex.