Abstract A fundamental problem in biomedical research is the low number of observations available, mostly due to a lack available biosamples, prohibitive costs, or ethical reasons. Augmenting few real with generated silico samples could lead more robust analysis results and higher reproducibility rate. Here, we propose use conditional single-cell generative adversarial neural networks (cscGAN) for realistic generation RNA-seq data. cscGAN learns non-linear gene–gene dependencies from...

We present Scaden, a deep neural network for cell deconvolution that uses gene expression information to infer the cellular composition of tissues. Scaden is trained on single-cell RNA sequencing (RNA-seq) data engineer discriminative features confer robustness bias and noise, making complex preprocessing feature selection unnecessary. demonstrate outperforms existing algorithms in both precision robustness. A single reliably deconvolves bulk RNA-seq microarray, human mouse tissue leverages...

The major benefits of driving vehicles in controlled close formations such as platoons are that increasing traffic fluidity and reducing air pollution. While Vehicle-toVehicle (V2V) communications is requisite for platooning stability, the existing radio technologies (e.g., IEEE 802.11p) suffer from poor performance highly dense road scenarios, which exactly to be created by platooning. This paper studies applicability visible light (VLC) system information exchange between platoon members....

Single-cell sequencing provides detailed insights into biological processes including cell differentiation and identity. While providing deep cell-specific information, the method suffers from technical constraints, most notably a limited number of expressed genes per cell, which leads to suboptimal clustering type identification.Here, we present DISCERN, novel generative network that precisely reconstructs missing single-cell gene expression using reference dataset. DISCERN outperforms...

Non-preemptive real-time scheduling and the corresponding schedulability analyses have received considerable less attention in research community, compared to preemptive scheduling. However, non-preemptive is widely used industry, especially case of hard systems where missing deadlines leads catastrophic situations resources must not be wasted. In many industries such as avionics tasks may strict periods, i.e. start times their executions separated by a fixed period. Indeed, this periodicity...

The Electrocardiogram ECG is one of the most important non-invasive tools for cardiac diseases diagnosis. Taking advantage developed telecommunication infrastructure, several approaches that address development telemetry devices were introduced recently. Telemetry allow easy and fast monitoring patients with suspected issues. Choosing right device desired working mode, signal quality, cost are still main obstacles to massive usage these devices. In this paper, we introduce design,...

Computational methods for predicting ship speed profile in a complex ice field have traditionally relied on mechanistic simulations. However, such difficulties capturing the entire complexity of ship–ice interaction process due to incomplete understanding underlying physical phenomena. Therefore, data-driven approaches recently gained increased attention this context. Hence, paper proposes concept first machine learning-based simulator field. The developed approach suggests using supervised...

Visible Light Communication (VLC) technology have recently been suggested as efficient supportive for platooning applications over short inter-vehicle distances. Though, ensuring the continuity of Line-of-Sight (LOS) any optical-based is one most complex scenarios an autonomous vehicle control, and still remains open challenge Intelligent Transformation Systems (ITS). Exchanging information about relative directional position each member platoon, together with front rear facing directions...

This research uses a new technique to accelerate the aging of samples prepared simulate those archaeological woolen fabrics. Natural dyed Fabric with turmeric and mordanted Alum, copper, potassium dichromate were stained three common stains found on textiles, namely; mud, oil, rust, then exposed UV/ozone for five different periods ranging from 5 min 120 min. The effect artificial fast surface morphology was studied by scanning electron microscope (SEM). In addition, mechanical behavior...

Abstract A fundamental problem in biomedical research is the low number of observations available, mostly due to a lack available biosamples, prohibitive costs, or ethical reasons. Augmenting few real with generated silico samples could lead more robust analysis results and higher reproducibility rate. Here we propose use conditional single cell Generative Adversarial Neural Networks (cscGANs) for realistic generation RNA-seq data. cscGANs learn non-linear gene-gene dependencies from...

In car-sharing applications and during certain time slots, some parking parks become full whereas others are empty. To redress this imbalance, vehicle redistribution strategies must be elaborated. As automatic relocation cannot in place, one alternative is to get a leader vehicle, driven by human, which come pick up drop off vehicles over the stations. This paper deals with problem among using strategy focuses on vehicle's platooning. We present an easy exit controller path planning based...

Abstract We present Scaden, a deep neural network for cell deconvolution that uses gene expression information to infer the cellular composition of tissues. Scaden is trained on single RNA-seq data engineer discriminative features confer robustness bias and noise, making complex preprocessing feature selection unnecessary. demonstrate outperforms existing algorithms in both precision robustness. A reliably deconvolves bulk microarray, human mouse tissue leverages combined multiple sets. Due...

This paper describes the development of a Cooperative Adaptive Cruise Control (CACC) for future urban transportation system at low-speed. The control algorithm was evaluated using two Cybecars as prototype vehicles. A longitudinal response model vehicles developed to design CACC system. implemented on fuzzy logic-based controller that has been tuned minimize cost function in order get trade-off between proper car-following gap error and smoothness signal. firstly tested simulation model....

We consider the problem of fixed priority scheduling non-preemptive strict periodic tasks in conjunction with sporadic preemptive tasks. There are few studies about combining these two kinds Moreover, only results available on since their performance analysis gives low success ratios, except case harmonic Also, great importance they charge for example sensors/actuators or feedback control functions which all critical systems. Such must have highest priorities order to guarantee a correct...

Recent developments in advanced driving assistance systems (ADAS) that rely on some level of autonomy have led the automobile industry and research community to investigate impact they might performance. However, most performed so far is based simulated environments. In this study we investigated behavior drivers a vehicle with automated system (ADS) capabilities real life scenario. We analyzed their response take over request (TOR) at two different speeds while being engaged...

Before the introduction of synthetic dyes in 1856, natural from plants and insects were commonly used to color fabrics. However, these are prone fading damage, posing challenges for conservators when cleaning, preserving, or displaying historical textiles. To address this issue, creating mimic samples that accurately replicate conditions valuable artifacts provides a opportunity conservation research testing materials. This study aims explore feasibility using UV/Ozone technique create...

Treatment and conservation operations are considered the most important processes for preserving cultural heritage collections, in particular archaeological textiles. This research outlines methods used treating an ancient piece of linen textile recovered from Qusayr excavations Red Sea. The was cleaned using traditional detergent "Orvus WA Paste surfactant", then, it consolidated to prevent damage combat microbiological attack silver nanoparticles loaded on hydroxypropyl cellulose polymer...

In this paper the usage of noise level approximation for adaptive Electromyogram (EMG) reduction in Electrocardiogram (ECG) signals is introduced. To achieve adequate adaptiveness, a translation-invariant employed. The done form guiding signal extracted as an estimation quality vs. EMG noise. framework based on bank low pass filters. So, achieved by selecting appropriate filter with respect to aiming obtain best trade-off between distortion caused filtering and readability. For evaluation...

In this paper we propose usage of neural networks in the field meteorology especially to detect ice formation on roads. Used algorithm for building and training network is based road air conditions which define road's surface. The ability self supervised learning are both used solve problem. We VHDL build proposed as a part detector. FPGA implementation done using Xilinx Spartan-3 device.

There are some archaeological bones resulting from excavations, and they have many different manifestations of damage such as brittleness, fragility weakness, through the aging samples that been strengthened with In this study, nano-hydroxyapatite concentrations 1% 2% + nano-paraloid concentration 3% dissolved in acetone an bone-strengthening substance .Visual assessment several analytical techniques were used for evaluation selected strengthening material .The transmission electron...