Search results for "55"

Multi-layer intrusion detection system with ExtraTrees feature selection, extreme learning machine ensemble, and softmax aggregation

2019

Abstract Recent advances in intrusion detection systems based on machine learning have indeed outperformed other techniques, but struggle with detecting multiple classes of attacks with high accuracy. We propose a method that works in three stages. First, the ExtraTrees classifier is used to select relevant features for each type of attack individually for each (ELM). Then, an ensemble of ELMs is used to detect each type of attack separately. Finally, the results of all ELMs are combined using a softmax layer to refine the results and increase the accuracy further. The intuition behind our system is that multi-class classification is quite difficult compared to binary classification. So, we…

Preamble Transmission Prediction for mMTC Bursty Traffic : A Machine Learning based Approach

2020

The evolution of Internet of things (IoT) towards massive IoT in recent years has stimulated a surge of traffic volume among which a huge amount of traffic is generated in the form of massive machine type communications. Consequently, existing network infrastructure is facing challenges when handling rapidly growing traffic load, especially under bursty traffic conditions which may more often lead to congestion. By proactively predicting the occurrence of congestion, we can implement necessary means and conceivably avoid congestion. In this paper, we propose a machine learning (ML) based model for predicting successful preamble transmissions at a base station and subsequently forecasting th…

Fall Detection Based on the Instantaneous Doppler Frequency : A Machine Learning Approach

2019

Modern societies are facing an ageing problem which comes with increased cost of healthcare. A major share of this ever-increasing cost is due to fall related injuries, which urges the development of fall detection systems. In this context, this paper paves the way for building of a radio-frequency-based fall detection system. This paper presents an activity simulator that generates the complex channel gain of indoor channels in the presence of one person performing three different activities, namely, slow fall, fast fall, and walking. We built a machine learning framework for activity recognition based on the complex channel gain. We assess the recognition accuracy of three different class…

Increasing sample efficiency in deep reinforcement learning using generative environment modelling

2020

The accretion flow to the intermittent accreting ms pulsar, HETE J1900.1-2455, as observed by XMM-Newton and RXTE

2012

We present a study of the accretion flow to the intermittent accreting millisecond pulsar, HETE J1900.1-2455, based on observations performed simultaneously by XMM-Newton and RXTE. The 0.33-50 keV spectrum is described by the sum of a hard Comptonized component originated in an optically thin {\tau}~1 corona, a soft kTin~0.2 keV component interpreted as accretion disc emission, and of disc reflection of the hard component. Two emission features are detected at energies of 0.98(1) and 6.58(7) keV, respectively. The latter is identified as K{\alpha} transition of Fe XXIII-XXV. A simultaneous detection in EPIC-pn, EPIC-MOS2, and RGS spectra favours an astrophysical origin also for the former, …

Aircraft-based observations of isoprene-epoxydiol-derived secondary organic aerosol (IEPOX-SOA) in the tropical upper troposphere over the Amazon reg…

2018

During the ACRIDICON-CHUVA field project (September–October 2014; based in Manaus, Brazil) aircraft-based in situ measurements of aerosol chemical composition were conducted in the tropical troposphere over the Amazon using the High Altitude and Long Range Research Aircraft (HALO), covering altitudes from the boundary layer (BL) height up to 14.4 km. The submicron non-refractory aerosol was characterized by flash-vaporization/electron impact-ionization aerosol particle mass spectrometry. The results show that significant secondary organic aerosol (SOA) formation by isoprene oxidation products occurs in the upper troposphere (UT), leading to increased organic aerosol mass concentratio…

Impact of the Asian monsoon on the extratropical lower stratosphere: trace gas observations during TACTS over Europe 2012

2016

Abstract. The transport of air masses originating from the Asian monsoon anticyclone into the extratropical upper troposphere and lower stratosphere (Ex-UTLS) above potential temperatures Θ =  380 K was identified during the HALO aircraft mission TACTS in August and September 2012. In situ measurements of CO, O3 and N2O during TACTS flight 2 on 30 August 2012 show the irreversible mixing of aged stratospheric air masses with younger (recently transported from the troposphere) ones within the Ex-UTLS. Backward trajectories calculated with the trajectory module of CLaMS indicate that these tropospherically affected air masses originate from the Asian monsoon anticyclone. These air masses are …

The novel HALO mini-DOAS instrument: inferring trace gas concentrations from airborne UV/visible limb spectroscopy under all skies using the scaling …

2017

Abstract. We report on a novel six-channel optical spectrometer (further on called mini-DOAS instrument) for airborne nadir and limb measurements of atmospheric trace gases, liquid and solid water, and spectral radiances in the UV/vis and NIR spectral ranges. The spectrometer was developed for measurements from aboard the German High-Altitude and Long-Range (HALO) research aircraft during dedicated research missions. Here we report on the relevant instrumental details and the novel scaling method used to infer the mixing ratios of UV/vis absorbing trace gases from their absorption measured in limb geometry. The uncertainties of the scaling method are assessed in more detail than before for …

SOUTHTRAC-GW: An airborne field campaign to explore gravity wave dynamics at the world’s strongest hotspot

2021

The southern part of South America and the Antarctic peninsula are known as the world’s strongest hotspot region of stratospheric gravity wave (GW) activity. Large tropospheric winds are deflected by the Andes and the Antarctic Peninsula and excite GWs that might propagate into the upper mesosphere. Satellite observations show large stratospheric GW activity above the mountains, the Drake Passage, and in a belt centered along 60°S. This scientifically highly interesting region for studying GW dynamics was the focus of the Southern Hemisphere Transport, Dynamics, and Chemistry–Gravity Waves (SOUTHTRAC-GW) mission. The German High Altitude and Long Range Research Aircraft (HALO) was deployed …

Cold cloud microphysical process rates in a global chemistry–climate model

2021

Microphysical processes in cold clouds which act as sources or sinks of hydrometeors below 0 ∘C control the ice crystal number concentrations (ICNCs) and in turn the cloud radiative effects. Estimating the relative importance of the cold cloud microphysical process rates is of fundamental importance to underpin the development of cloud parameterizations for weather, atmospheric chemistry, and climate models and to compare the output with observations at different temporal resolutions. This study quantifies and investigates the ICNC rates of cold cloud microphysical processes by means of the chemistry–climate model EMAC (ECHAM/MESSy Atmospheric Chemistry) and defines the hierarchy of sources…