Recent advances in wireless technologies have led to several autonomous deployments of such networks. As nodes across distributed networks must co-exist, it is important that all transmitters and ...receivers are aware of their radio frequency (RF) surroundings so that they can adapt their transmission and reception parameters to best suit their needs. To this end, machine learning techniques have become popular as they can learn, analyze and predict the RF signals and associated parameters that characterize the RF environment. However, in the presence of adversaries, malicious activities such as jamming and spoofing are inevitable, making most machine learning techniques ineffective in such environments. In this paper we propose the Radio Frequency Adversarial Learning (RFAL) framework for building a robust system to identify rogue RF transmitters by designing and implementing a generative adversarial net (GAN). We hope to exploit transmitter specific "signatures" like the in-phase (I) and quadrature (Q) imbalance (i.e., the I/Q imbalance ) present in all transmitters for this task, by learning feature representations using a deep neural network that uses the I/Q data from received signals as input. After detection and elimination of the adversarial transmitters RFAL further uses this learned feature embedding as "fingerprints" for categorizing the trusted transmitters. More specifically, we implement a generative model that learns the sample space of the I/Q values of known transmitters and uses the learned representation to generate signals that imitate the transmissions of these transmitters. We program 8 universal software radio peripheral (USRP) software defined radios (SDRs) as trusted transmitters and collect "over-the-air" raw I/Q data from them using a Realtek Software Defined Radio (RTL-SDR), in a laboratory setting. We also implement a discriminator model that discriminates between the trusted transmitters and the counterfeit ones with 99.9% accuracy and is trained in the GAN framework using data from the generator. Finally, after elimination of the adversarial transmitters, the trusted transmitters are classified using a convolutional neural network (CNN), a fully connected deep neural network (DNN) and a recurrent neural network (RNN) to demonstrate building of an end-to-end robust transmitter identification system with RFAL. Experimental results reveal that the CNN, DNN, and RNN are able to correctly distinguish between the 8 trusted transmitters with 81.6%, 94.6% and 97% accuracy respectively. We also show that better "trusted transmission" classification accuracy is achieved for all three types of neural networks when data from two different types of transmitters (different manufacturers) are used rather than when using the same type of transmitter (same manufacturer).
Deep Neural Networks (DNNs) have become the tool of choice for machine learning practitioners today. One important aspect of designing a neural network is the choice of the activation function to be ...used at the neurons of the different layers. In this work, we introduce a four-output activation function called the Reflected Rectified Linear Unit (RReLU) activation which considers both a feature and its negation during computation. Our activation function is "sparse", in that only two of the four possible outputs are active at a given time. We test our activation function on the standard MNIST and CIFAR-10 datasets, which are classification problems, as well as on a novel Computational Fluid Dynamics (CFD) dataset which is posed as a regression problem. On the baseline network for the MNIST dataset, having two hidden layers, our activation function improves the validation accuracy from 0.09 to 0.97 compared to the well-known ReLU activation. For the CIFAR-10 dataset, we use a deep baseline network that achieves 0.78 validation accuracy with 20 epochs but overfits the data. Using the RReLU activation, we can achieve the same accuracy without overfitting the data. For the CFD dataset, we show that the RReLU activation can reduce the number of epochs from 100 (using ReLU) to 10 while obtaining the same levels of performance.
Transient receptor potential ankyrin 1 (TRPA1) channels are known to be actively involved in various pathophysiological conditions, including neuronal inflammation, neuropathic pain, and various ...immunological responses. Heat shock protein 90 (Hsp90), a cytoplasmic molecular chaperone, is well-reported for various cellular and physiological processes. Hsp90 inhibition by various molecules has garnered importance for its therapeutic significance in the downregulation of inflammation and are proposed as anti-cancer drugs. However, the possible role of TRPA1 in the Hsp90-associated modulation of immune responses remains scanty.
Here, we have investigated the role of TRPA1 in regulating the anti-inflammatory effect of Hsp90 inhibition via 17-(allylamino)-17-demethoxygeldanamycin (17-AAG) in lipopolysaccharide (LPS) or phorbol 12-myristate 13-acetate (PMA) stimulation in RAW 264.7, a mouse macrophage cell lines and PMA differentiated THP-1, a human monocytic cell line similar to macrophages. Activation of TRPA1 with Allyl isothiocyanate (AITC) is observed to execute an anti-inflammatory role via augmenting Hsp90 inhibition-mediated anti-inflammatory responses towards LPS or PMA stimulation in macrophages, whereas inhibition of TRPA1 by 1,2,3,6-Tetrahydro-1,3-dimethyl-N-4-(1-methylethyl)phenyl-2,6-dioxo-7 H-purine-7-acetamide,2-(1,3-Dimethyl-2,6-dioxo-1,2,3,6-tetrahydro-7 H-purin-7-yl)-N-(4-isopropylphenyl)acetamide (HC-030031) downregulates these developments. LPS or PMA-induced macrophage activation was found to be regulated by TRPA1. The same was confirmed by studying the levels of activation markers (major histocompatibility complex II (MHCII), cluster of differentiation (CD) 80 (CD80), and CD86, pro-inflammatory cytokines (tumor necrosis factor (TNF) and interleukin 6 (IL-6)), NO (nitric oxide) production, differential expression of mitogen-activated protein kinase (MAPK) signaling pathways (p-p38 MAPK, phospho-extracellular signal-regulated kinase 1/2 (p-ERK 1/2), and phosphor-stress-activated protein kinase/c-Jun N-terminal kinase (p-SAPK/JNK)), and induction of apoptosis. Additionally, TRPA1 has been found to be an important contributor to intracellular calcium levels toward Hsp90 inhibition in LPS or PMA-stimulated macrophages.
This study indicates a significant role of TRPA1 in Hsp90 inhibition-mediated anti-inflammatory developments in LPS or PMA-stimulated macrophages. Activation of TRPA1 and inhibition of Hsp90 has synergistic roles towards regulating inflammatory responses associated with macrophages. The role of TRPA1 in Hsp90 inhibition-mediated modulation of macrophage responses may provide insights towards designing future novel therapeutic approaches to regulate various inflammatory responses.
Celotno besedilo
Dostopno za:
DOBA, IZUM, KILJ, NUK, PILJ, PNG, SAZU, SIK, UILJ, UKNU, UL, UM, UPUK
In this work we implement an automatic emitter identification system using three dimensional convolutional neural networks (3D-CNN). We show that it is possible to leverage the short term ...spatio-temporal properties of the raw I/Q signal data using 3D-CNN and apply this to the task of transmitter identification. The time series of raw I/Q signal data exhibits a "helical" structure which encodes the intrinsic properties of the emitter as short term variations. These features are exploited by our system to create unique "fingerprints" for the emitters, which are finally used for the task of identification. Our system is end-to-end, works with the raw I/Q signal data and is able to automatically discriminate between different transmitters without using a recurrent structure, thus reducing the complexity of the system. We experimented with four novel RF transmitter datasets that we curated in an uncalibrated and uncontrolled indoor environment. The first dataset consists of four identical transmitters, the second eight identical transmitters, the third four heterogeneous transmitters and the last eight heterogeneous transmitters. We use Ettus Research USRP Software Defined Radios (USRP B210, B200, X310), ADLM Pluto and BladeRF for transmission and collect the raw signal data using a RTL Software Defined Radio (RTL SDR) receiver dongle, from each of the four and eight emitters at a time. We use the data to train and test the 3D convolutional neural network for discerning intrinsic transmitter characteristics for the task of classification. Through our methods and implementation, we show that we can identify the transmitters with ~99 % accuracy.
Science users typically obtain data from authoritative or trusted sources referred to as repositories . An authoritative source is defined as an entity that is approved by a legal entity to develop ...or manage data for a specific purpose <xref ref-type="bibr" rid="ref4">4 , <xref ref-type="bibr" rid="ref5">5 . Different government agencies generating Earth observation (EO) data are one example. An authoritative source can also be an actively managed repository of valid or trusted data that is recognized by a community and supports data governance and stewardship practices. One can also have secondary sources that serve as trusted sources and provide trusted data <xref ref-type="bibr" rid="ref6">6 . A trusted source can be a service provider or an organization that publishes data obtained from a number of authoritative sources. These publications are often compilations and subsets of the data from more than one authoritative source. They are "trusted" because there is an "official process and/or agreement" for compiling the data from authoritative sources, data are actively managed, and the limitations, currency, and attributes are known and documented. NASA mirroring Sentinel-1 data from the European Space Agency is one such example of a trusted source.
Due to the great achievements in the field of optimization of the design of cyclone separators, non-standard solutions are sought to increase their performance. Therefore, in this study, we consider ...the impact of different cone and cylinder height variants on the performance of cyclone separators. Additionally, we propose non-standard shapes for these sections. Three different heights: H/D = 0.5, 1.0, and 1.5, with D (the main cyclone body diameter), are analyzed. Since the cone is one of the most important geometrical entities, three different shapes viz. a straight (conventional) profile, a concave profile as well as a convex profile are also taken into account. Cyclone performance is rated at three different inlet velocities viz. Uin = 10 m/s, 15 m/s, and 20 m/s. Hence, a total of 27 simulations have been performed using the Reynolds stress model. It becomes apparent from the present study that the pressure loss is lowest in the convex variant, whereas the separation efficiency is better in the conventional design. Furthermore, an increase in the length of the cylindrical section reduces pressure drop with a mild decrease in the collection efficiency in all variants.
Toll like receptor 4 (TLR4), a pathogen-associated molecular pattern (PAMP) receptor, is known to exert inflammation in various cases of microbial infection, cancer and autoimmune disorders. However, ...any such involvement of TLR4 in Chikungunya virus (CHIKV) infection is yet to be explored. Accordingly, the role of TLR4 was investigated towards CHIKV infection and modulation of host immune responses in the current study using mice macrophage cell line RAW264.7, primary macrophage cells of different origins and
mice model. The findings suggest that TLR4 inhibition using TAK-242 (a specific pharmacological inhibitor) reduces viral copy number as well as reduces the CHIKV-E2 protein level significantly using p38 and JNK-MAPK pathways. Moreover, this led to reduced expression of macrophage activation markers like CD14, CD86, MHC-II and pro-inflammatory cytokines (TNF, IL-6, MCP-1) significantly in both the mouse primary macrophages and RAW264.7 cell line,
. Additionally, TAK-242-directed TLR4 inhibition demonstrated a significant reduction of percent E2-positive cells, viral titre and TNF expression in hPBMC-derived macrophages,
. These observations were further validated in TLR4-knockout (KO) RAW cells. Furthermore, the interaction between CHIKV-E2 and TLR4 was demonstrated by immuno-precipitation studies,
and supported by molecular docking analysis,
TLR4-dependent viral entry was further validated by an anti-TLR4 antibody-mediated blocking experiment. It was noticed that TLR4 is necessary for the early events of viral infection, especially during the attachment and entry stages. Interestingly, it was also observed that TLR4 is not involved in the post-entry stages of CHIKV infection in host macrophages. The administration of TAK-242 decreased CHIKV infection significantly by reducing disease manifestations, improving survivability (around 75%) and reducing inflammation in mice model. Collectively, for the first time, this study reports TLR4 as one of the novel receptors to facilitate the attachment and entry of CHIKV in host macrophages, the TLR4-CHIKV-E2 interactions are essential for efficient viral entry and modulation of infection-induced pro-inflammatory responses in host macrophages, which might have translational implication for designing future therapeutics to regulate the CHIKV infection.
This paper presents a robust system for mitigating adversarial and natural GPS disruptions by presenting: (1) a software-based defense mechanism against spoofing attacks using generative adversarial ...networks (GANs), The system detects unauthorized or spoofed GPS signals from a hardware based spoofer, and (2) deep neural network models to infer positioning information in GPS-degraded /denied environments using the novel idea of GPS satellite constellation fingerprint. As the GAN and Satellite constellation fingerprinting are used together in a unified framework, we call it the "GANSAT positioning system." Intuitively, the GANSAT neural networks implicitly learn a representation of the aggregation of the hardware fingerprints of the satellite's in the GPS constellation at a given location and time. To demonstrate the approach, raw GPS signals were collected from the satellite transmitters using a software defined radio (SDR) at five different locations in the Florida panhandle area of the United States. Additionally, a GPS spoofer is implemented using a SDR and an open source software and used in an uncontrolled laboratory environment for spoofing the GPS signals at the aforementioned locations. In our experiments, the GANSAT framework yields ~99.5% accuracy for the task of identifying and filtering the spoofed GPS signals from real ones. It also achieves ~100% accuracy for the task of location estimation.
In this paper we consider the problem of "end-to-end" digital camera identification by considering sequence of images obtained from the cameras. The problem of digital camera identification is harder ...than the problem of identifying its analog counterpart since the process of analog to digital conversion smooths out the intrinsic noise in the analog signal. However it is known that identifying a digital camera is possible by analyzing the camera's intrinsic sensor artifacts that are introduced into the images/videos during the process of photo/video capture. It is known that such methods are computationally intensive requiring expensive pre-processing steps. In this paper we propose an end-to-end deep feature learning framework for identifying cameras using images obtained from them. We conduct experiments using three custom datasets: the first containing two cameras in an indoor environment where each camera may observe different scenes having no overlapping features, the second containing images from four cameras in an outdoor setting but where each camera observes scenes having overlapping features and the third containing images from two cameras observing the same checkerboard pattern in an indoor setting. Our results show that it is possible to capture the intrinsic hardware signature of the cameras using deep feature representations in an end-to-end framework. These deep feature maps can in turn be used to disambiguate the cameras from each another. Our system is end-to-end, requires no complicated pre-processing steps and the trained model is computationally efficient during testing, paving a way to have near instantaneous decisions for the problem of digital camera identification in production environments. Finally we present comparisons against the current state-of-the-art in digital camera identification which clearly establishes the superiority of the end-to-end solution.
The bicyclic 4‐nitroimidazoles PA‐824 and OPC‐67683 represent a promising novel class of therapeutics for tuberculosis and are currently in phase II clinical development. Both compounds are pro‐drugs ...that are reductively activated by a deazaflavin (F420) dependent nitroreductase (Ddn). Herein we describe the biochemical properties of Ddn including the optimal enzymatic turnover conditions and substrate specificity. The preference of the enzyme for the (S) isomer of PA‐824 over the (R) isomer is directed by the presence of a long hydrophobic tail. Nitroimidazo‐oxazoles bearing only short alkyl substituents at the C‐7 position of the oxazole were reduced by Ddn without any stereochemical preference. However, with bulkier substitutions on the tail of the oxazole, Ddn displayed stereospecificity. Ddn mediated metabolism of PA‐824 results in the release of reactive nitrogen species. We have employed a direct chemiluminescence based nitric oxide (NO) detection assay to measure the kinetics of NO production by Ddn. Binding affinity of PA‐824 to Ddn was monitored through intrinsic fluorescence quenching of the protein facilitating a turnover‐independent assessment of affinity. Our results indicate that (R)‐PA‐824, despite not being turned over by Ddn, binds to the enzyme with the same affinity as the active (S) isomer. This result, in combination with docking studies in the active site, suggests that the (R) isomer probably has a different binding mode than the (S) with the C‐3 of the imidazole ring orienting in a non‐productive position with respect to the incoming hydride from F420. The results presented provide insight into the biochemical mechanism of reduction and elucidate structural features important for understanding substrate binding.
PA‐824, a bicyclic‐nitroimidazole in clinical development against tuberculosis, is bioreductively activated by a deazaflavin (F420) dependent nitroreductase (Ddn). Substrate and stereospecificity of Ddn is directed by the presence of a long hydrophobic tail. (R)‐PA‐824 binds Ddn with the same affinity as the active (S)‐PA‐824, despite not being turned over. Docking studies suggest that (R)‐PA‐824 likely binds non‐productively to the enzyme.