Bulk heterojunction photovoltaic devices based on blends of a conjugated polymer poly[2-methoxy-5-(3',7'-dimethyloctyloxy)-1,4-phenylenevinylene] (MDMO-PPV) as electron donor and crystalline ZnO nanoparticles (nc-ZnO) acceptor have been studied. Composite nc-ZnO:MDMO-PPV films were cast from common solvent mixture. Time-resolved pump-probe spectroscopy revealed that photoinduced transfer MDMO-PPV to nc-ZnO occurs in these sub-picosecond time scale produces long-lived (milliseconds)...

Abstract The performance of bulk‐heterojunction solar cells based on a phase‐separated mixture donor and acceptor materials is known to be critically dependent the morphology active layer. Here we use combination techniques resolve spin cast films poly( p ‐phenylene vinylene)/methanofullerene blends in three dimensions nanometer scale relate results corresponding cells. Atomic force microscopy (AFM), transmission electron (TEM), depth profiling using dynamic time‐of‐flight secondary ion mass...

Spectrum sensing is a key technology for cognitive radios. We present spectrum as classification problem and propose method based on deep learning classification. normalize the received signal power to overcome effects of noise uncertainty. train model with many types signals possible well data enable trained network adapt untrained new signals. also use transfer strategies improve performance real-world Extensive experiments are conducted evaluate this method. The simulation results show...

The mobile and flexible unmanned aerial vehicle (UAV) with edge computing (MEC) can effectively relieve the pressure of massive data traffic in 5G Internet Things. In this paper, we propose a novel online learning offloading (OELO) scheme for UAV-assisted MEC secure communications, which improve computation performance. Moreover, problem information security is further considered since terminal users (TUs) may be eavesdropped due to light-of-sight characteristic UAV transmission. OELO...

The influence of various thermal treatment steps on the morphology and photoconductive properties a non-contacted, 50 nm thick blend (50:50 wt.-%) [6,6]-phenyl C61-butyric acid methyl ester (PCBM) poly(3-hexyl thiophene) (P3HT) spin-coated from chloroform has been studied using transmission electron microscopy (TEM) electrodeless time-resolved microwave conductivity technique. After annealing film for 5 min at 80 °C, TEM images show formation crystalline fibrils P3HT due to more ordered...

An automatic modulation classification has a very broad application in wireless communications. Recently, deep learning been used to solve this problem and achieved superior performance. In most cases, the input size is fixed convolutional neural network (CNN)-based classification. However, duration of actual radio signal burst variable. When length greater than CNN length, how make full use complete improve accuracy needs be considered. paper, three fusion methods are proposed problem, such...

Community detection plays an important role in social networks, since it can help to naturally divide the network into smaller parts so as simplify analysis. However, on other hand, arises concern that individual information may be overmined, and concept community deception has been proposed protect privacy networks. Here, we introduce formalize problem of attack develop efficient strategies algorithms by rewiring a small number connections, leading protection. In particular, first give two...

A canonical wireless communication system consists of a transmitter and receiver. The information bit stream is transmitted after coding, modulation, pulse shaping. Due to the effects radio frequency (RF) impairments, channel fading, noise interference, signal arriving at receiver will be distorted. needs recover original from distorted signal. In this paper, we propose new model, namely DeepReceiver, that uses deep neural network replace traditional receiver's entire recovery process. We...

Deep neural networks are becoming popular and important assets of many AI companies. However, recent studies indicate that they also vulnerable to adversarial attacks. Adversarial attacks can be either white-box or black-box. The assume full knowledge the models while black-box ones none. In general, revealing more internal information enable much powerful efficient in most real-world applications, embedded devices is unavailable. Therefore, this brief, we propose a side-channel based...

Our digital world is full of time series and graphs which capture the various aspects many complex systems. Traditionally, there are respective methods in processing these two different types data, e.g., Recurrent Neural Network (RNN) Graph (GNN), while recent years, could be mapped to by using techniques such as Visibility (VG), simultaneously captures relevant both local global dynamics an easy way, so that researchers can use graph algorithms mine knowledge gain special latent...

Automatic modulation classification (AMC) can generally be divided into knowledge-based methods and data-driven methods. In this paper, we explore combining the method technology to take full advantage of both propose a hybrid knowledge deep learning framework (HKDD) for AMC. To make handcrafted features more discriminative, various traditional are adopted, including instantaneous features, statistical spectral features. HKDD framework, feature fusion mechanism is proposed integrate learned...

Direction-of-arrival (DOA) estimation is a vital research topic in array signal processing, with extensive applications many fields. In recent years, deep learning has been applied to DOA improve the performance. However, most existing learning-based methods extract information from covariance matrix (CM) input. this paper, we introduce novel scheme that utilizes raw in-phase (I) and quadrature (Q) components of as We formulate problem single-label classification multi-label based on number...

Abstract Integrated sensing and communication (ISAC) is a promising technique to increase spectral efficiency support various emerging applications by sharing the spectrum hardware between these functionalities. However, traditional ISAC schemes are highly dependent on accurate mathematical model suffer from challenges of high complexity poor performance in practical scenarios. Recently, artificial intelligence (AI) has emerged as viable address issues due its powerful learning capabilities,...

The morphological evolution of thin composite films based on poly(3-hexylthiophene) (P3HT) and [6,6]-phenyl C61 butyric acid methyl ester (PCBM) upon annealing has been studied by means transmission electron microscopy (TEM), scanning near-field optical (SNOM), confocal Raman microscopy. This system currently is the most promising candidate for high-performance polymer solar cells. TEM bright field SNOM topography measurements show that segregation large-scale crystallization PCBM take place...

Photovoltaic properties of solution-processed semiconducting polymer blends have been studied. It is demonstrated that photoinduced charge transfer occurs in binary mixtures poly[2-methoxy-5-(3,7-dimethyloctyloxy)-1,4-phenylenevinylene] (MDMO−PPV) and poly[oxa-1,4-phenylene-(1-cyano-1,2-vinylene)−(2-methoxy-5-(3,7-dimethyloctyloxy)-1,4-phenylene)-1,2-(2-cyanovinylene)-1,4-phenylene] (PCNEPV). Further, it shown the photovoltaic performance improved by a thermal treatment which alters...

Radio signal classification has a very wide range of applications in the field wireless communications and electromagnetic spectrum management. In recent years, deep learning been used to solve problem radio achieved good results. However, data currently is limited scale. order verify performance learning-based on real-world data, this paper we conduct experiments large-scale ACARS ADS-B with sample sizes 900,000 13,000,000, respectively, categories 3,143 5,157 respectively. We use same...

In modern society, the demand for radio spectrum resources is increasing. As information carriers of wireless transmission data, signals exhibit characteristics big data in terms volume, variety, value, and velocity. How to uniformly handle these obtain value from them a problem that needs be studied. this paper, processing architecture presented new approach end-to-end signal based on deep learning discussed detail. The intelligent search engine used as an example verify architecture,...

Deep learning methods achieve great success in many areas due to their powerful feature extraction capabilities and end-to-end training mechanism, recently they are also introduced for radio signal modulation classification. In this paper, we propose a novel deep framework called SigNet, where signal-to-matrix (S2M) operator is adopted convert the original into square matrix first co-trained with follow-up CNN architecture This model further accelerated by integrating 1D convolution...

Deep learning has been widely exploited in radio modulation recognition recent years. In this paper, we exploit empirical mode decomposition (EMD) and variational (VMD) deep learning-based recognition. The received IQ sequences are decomposed by EMD or VMD the components spliced fed into designed neural network for classification. order to reduce computational complexity, further propose dowansample input these downsampled Simulation results show that proposed methods perform far better than...

On-chip microring resonators (MRRs) have been proposed to construct time-delayed reservoir computing (RC) systems, which offer promising configurations available for computation with high scalability, high-density computing, and easy fabrication. A single MRR, however, is inadequate provide enough memory the task diverse requirements. Large requirements are satisfied by RC system based on MRR optical feedback, but at expense of its ultralong feedback waveguide. In this paper, a utilizing...

Generative adversarial network (GAN) has achieved great success in many fields such as computer vision, speech processing, and natural language because of its powerful capabilities for generating realistic samples. In this paper, we introduce GAN into the field electromagnetic signal classification (ESC). ESC plays an important role both military civilian domains. However, specific scenarios, can't obtain enough labeled data, which cause failure deep learning methods they are easy to fall...

The nonlinear variation of viewing angles over a long duration causes initial phase the received pulse in passive positioning system with single moving receiver. Typical systems ignore and perform incoherent accumulation long-time data, resulting decrease accuracy, especially at low signal-to-noise ratio (SNR). A novel synthetic aperture technique, named (SAP) system, is proposed to resolve issue. First, new 2-dimensional (2-D) continuous sampling working model proposed. Then, SAP cost...

Deep learning has been widely used in automatic modulation classification (AMC) recently. Most of deep learning-based AMC uses a single network model to deal with radio signals input format. In this paper, we propose hybrid heterogeneous architecture named DeepSIG, which integrates Recurrent Neural Network (RNN), Convolutional (CNN) and Graph (GNN) models framework process formats, i.e., in-phase (I) quadrature (Q) sequences, images mapped from IQ graphs converted signals, extract integrate...