Human-machine systems required a deep understanding of human behaviors. Most existing research on action recognition has focused discriminating between different actions, however, the quality executing an received little attention thus far. In this paper, we study assessment driving behaviors and present WiQ, system to assess actions based radio signals. This includes three key components, neural network learning engine extract information from changes signal strength, gradient-based method...

Porous carbon materials derived from waste biomass are promising adsorbents for volatile organic compounds. However, it is still difficult to achieve optimal control of the pore structure. In this study, a nitrogen-doped porous (NPC) material with ultra-high surface area (3235 m2/g) and ultra-large volume (2.00 cm3/g) was prepared. The adsorption capacity toluene on NPC (691.1 mg/g, 1000 ppm, 303 K) significantly higher than previous studies. addition, correlations between capacity, as well...

Recently, WiFi-based gesture recognition has attracted increasing attention. Due to the sensitivity of WiFi signals environments, an activity model trained at a specific place can hardly work well for other places. To tackle this challenge, we propose WiHand, location independent system based on commodity devices. Leveraging low rank and sparse decomposition, WiHand separates signal from background information, thus making it resilient variation. Extensive evaluations showed that achieve...

Coordination among users is an indispensable part in wireless networks for efficient medium access. Alone with the rapid increase of transmission rate, however, coordination time becomes insufferable. We present AFD, namely asymmetric full duplex, to achieve high efficiency at nearly zero overhead. In channel contention performed simultaneously data transmission. propose a 3D pipeline scheme where process divided into several parallel stages and executed pipelined manner domain specified by...

Ear recognition is proved to be a promising authentication technique. Because of earpsilas special physiological structure and location, the fusion ear face biometrics could fully utilize their connection relationship location supplement between these two biometrics, possess advantage recognizing people without cooperation. In this paper novel feature algorithm based on KFDA proposed applied multimodal profile face. With algorithm, discriminant vectors are established nonlinear projection...

Due to dynamic channel availability in cognitive radio networks (CRNs), rendezvous problem is known as the most challenging issue design of media access control (MAC) protocol, which a key step for secondary users (SUs) start communication. With concept blind rendezvous, numerous channel-hopping sequence (CHS) based schemes have been proposed solve this these years. Currently, little attention paid carrier sensing multiple access/collision avoidance (CSMA/CA) MAC on and also...

Because of ear's special physiological structure and location, it is reasonable to combine ear with profile face for recognition in such scenarios as frontal images are not available. In this paper, a novel method multimodal fusing based on kernel principal component analysis proposed. With the algorithm, fusion feature vectors established nonlinear projection could be implemented. The experimental results show that both improvement over either or unimodal recognition.

Dissolved Gas Analysis (DGA) in oil is one of the most commonly used methods for transformer fault diagnosis, and artificial intelligence an effective means to realize faults. However, due large difference number samples different types transformers, a single method combined with DGA prone bias parameter update majority class while ignoring correct classification minority during goal realization process. In order improve diagnosis accuracy unbalanced sample scenario, this paper proposed...

For the purpose of improving predictive accuracy and interpretability telecom customer retention prediction model, MBBCTree Algorithm, which integrates advantage Markov Blanket Bayesian Networks (MBBC) Decision Tree, is proposed in this paper to predict customers' lifetime. classifier uses a tree structure split instance space into sub-spaces generates one MBBC each sub-space. Experimental results show that new algorithm outperforms Naïve-Bayes Tree (NBTree), Naïve Bayes classifiers...

The available cases with actual classes are not enough for building telecom clients' credit classification model in practice, especially the newly established system which old customers' data do exist. For evaluating credit, a classifier based on active learning is proposed this paper. Active aims at reducing number of training examples to be labeled by automatically processing unlabeled examples, then selecting most informative ones respect given cost function human label. Experimental...

In consideration of the continuous increasing demand wireless data transmission, ultra-wideband spectrum sensing is crucial to support cognitive communication in a ultra-wide frequency band. However, it challenging design ADCs that fulfill Nyquist rate requirement for ultra wide Spectrum based on sub-Nyquist sampling maybe answer. We propose UWBSS: sensing. With multiple rates, UWBSS can reconstruct occupied frequencies from under sampled directly without complex amplitudes reconstruction....

Hidden terminal and collisions are well-known problems due to broadcasting nature of wireless network. In this paper, we address an efficient MAC protocol evade the potential caused by hidden terminals, where advanced phycical layer technique, full-duplex, is exploited coordinate channel contention among nodes within two-hops range. Furhter-more, cooperative hopping(CCH) developed improve frequency efficiency limiting interference terminals enabling a collision-free for further transmission....

Coordination among users is an inevitable but time-consuming operation in wireless networks. It severely limit the system performance when data rate high. We present FC-MAC, a novel MAC protocol that can complete contention within one slot over joint frequency-code domain. When node takes part contention, it generates randomly vector (CV), which binary sequence of length equal to number available orthogonal frequency division multiplexing (OFDM) subcarriers. In different user assigned with...

To satisfy the reliability of real-time wireless multimedia multicast services, existing erasure error correction schemes usually assume that packet size in transmissions is fixed.However, recent studies have shown Variable Packet Size (VPS) can deeply influence performance unicast services.Accordingly, using a delay-limited general architecture EEC for multicast, this paper proposes an Adaptive Hybrid Error Correction (AHEC) scheme with VPS.Comparing AHEC fixed size, analysis results show...

Accurate short-term load forecasting (STLF) is an important aspect for the safe and stable operation of power system. When multiple factors are taken into consideration, input data preprocessing method variable selection strategy essential improving accuracy STLF. In this article, both discussed, two improved algorithms proposed to deal with massive data. Firstly, a cosine similarity-based cluster analysis introduced enhance efficiency model learning by extracting information time variables...

MBBNTree algorithm, which integrates the advantage of Markov blanket Bayesian networks (MBBN) and decision tree, would behave better performance than other for classification. But available training samples with actual classes are not enough building classifier in practice. Active learning aims at reducing number examples to be labeled by automatically processing unlabeled examples, then selecting most informative ones respect a given cost function human label. In this paper, algorithm based...

With the ever-increasing demand for high-speed wireless data transmission, ultra-wideband spectrum sensing is critical to support cognitive communication over an ultra-wide frequency band systems. However, it challenging analog-to-digital converter design fulfill Nyquist rate band. Therefore, we explore mechanism based on sub-Nyquist sampling and conduct extensive experiments investigate influence of rate, bandwidth resolution signal-to-noise ratio accuracy sensing. Afterward, adaptive...

With the rapid development of superconducting technology, electrical properties insulating materials in low temperature have recently gained more and attention. In this paper, Alternating Current (AC) negative Direct (DC) breakdown strength polyimide (PI), polyester (PET) polytetrafluoroethylene (PTFE) been tested room liquid nitrogen environment respectively by using different electrode system. The results show that DC these three kinds material is lower than temperature, AC PTFE PI has a...

An efficient facial representation is a crucial step for successful and effective performance of cognitive tasks such as object recognition, fixation, recognition system, etc. This paper demonstrates the use Gabor wavelets transform recognition. Facial influenced by several factors shape, reflectance, pose, occlusion illumination which make it even more difficult. wavelet used features vector construction due to its powerful behavior receptive fields in human visual system (HVS). The method...

Traditional wireless relay networks have large end-to-end time delay and low throughput because of the limit that it can't receive forward at same time. In this paper, we proposed IWFR: Immediate Wireless Full-Duplex Relay which exploits advantages full-duplex to shorten improve throughput. At time, designed a new implicit acknowledgement mechanism, can eliminate ACK overheads evidently relay. To implement IWFR, also modified node architecture make support for immediate Simulation shows IWFR...

Since the strong coupling property between partial discharge and external interference, how to obtain an acceptable Resolution is a huge challenge during measure. In terms of interference suppression, many methods associated with analog digital technique are devised. Whatever are, way eliminate pulse toughest task due closest feature in respect time frequency field compared discharge. this paper, we propose wavelet based separation method separate signal compounding random signal, mobile...

Large bandwidth is indispensable for future high-speed wireless transmission. However, implementation of traditional receiver demands ultra-high-speed ADC to receive large-bandwidth signals, which challenging current manufacturing. Motivated defeat this challenge, we propose STTGR, literally extracted from stitching-together receiving. STTGR a extension receiving scheme by means frequency stitching-together. Considering the immense potential OFDM in communication, specialized signals....

One of the most important topics in Human-Centered Computing (HCC) is to recognise human's activities. In this paper, technology wireless-based activity recognition introduced. By using wireless signals, one can achieve Non-Line-Of-Sight (NLOS) without carrying any devices. Also, it easy deploy a system due ubiquity communication systems. The basic idea detect different characteristics signal propagation that correspond distinct human behaviors. As result, action performed by analyzing...

Reasonable capacity expansion optimization of determined charging stations is important for the popularization electric vehicles (EVs). In this article, Gaussian two-step floating catchment area method and temporal clustering are adopted to study unbalanced spatial distribution station accessibility, as well determine candidate sites optimization. Then, a two-level model proposed reduce computational complexity caused by non-linearity non-convexity choice probability formulas when discrete...

Dynamic wireless charging technology has emerged, enabling electric vehicles to charge while in motion. Considering the substantial cost associated with dynamic charging, it is evident that plug-in and will coexist for an extended period. To address current research gap concerning selection of infrastructure locations multiple types vehicles, including gasoline-powered ones, a bi-level optimization model proposed. The upper-level aims determine optimal facility within given budget,...