This paper studies an Internet congestion control system with two time delays, which are accessed by a single resource and considers both discrete and distributed delays of the system. By designing a new hybrid contro...
详细信息
This paper studies an Internet congestion control system with two time delays, which are accessed by a single resource and considers both discrete and distributed delays of the system. By designing a new hybrid controller containing negative feedback control and time delay feedback control to control the system, and taking discrete time delay variables as bifurcation parameters, the local stability and Hopf bifurcation of the system are studied. The results show that the Hopf bifurcation can be effectively delayed or avoided by adjusting the value of the feedback control parameter beta. The global asymptotically stable dynamic characteristics of the system are ideal, which has important functional significance for optimizing network congestion control. Finally, a large number of simulation examples verify the correctness of the conclusions.
The phase-sensitive optical time domain reflectometry (Phi-OTDR) technique offers a method for distributed acoustic sensing (DAS) systems to detect external acoustic fluctuations and mechanical vibrations. By accurate...
详细信息
The phase-sensitive optical time domain reflectometry (Phi-OTDR) technique offers a method for distributed acoustic sensing (DAS) systems to detect external acoustic fluctuations and mechanical vibrations. By accurately identifying vibration events, DAS systems provide a non-invasive solution for security monitoring. However, limitations in temporal signal analysis and the lack of spatial features significantly impact classification accuracy in event recognition. To address these challenges, this paper proposes a network model for vibration-event recognition that integrates convolutional neuralnetworks (CNNs), bidirectional gated recurrent units (BiGRUs), and attention mechanisms, referred to as CNN-BiGRU-Attention (CBA). First, the CBA model processes spatiotemporal matrices converted from raw signals, extracting low-level features through convolution and pooling. Subsequently, features are further extracted and separated along both the temporal and spatial dimensions. In the spatial-dimension branch, horizontal convolution and pooling generate enhanced spatial feature maps. In the temporal-dimension branch, vertical convolution and pooling are followed by BiGRU processing to capture dynamic changes in vibration events from both past and future contexts. Additionally, the attention mechanism focuses on extracted features in both dimensions. The features from the two dimensions are then fused using two cross-attention mechanisms. Finally, classification probabilities are output through a fully connected layer and a softmax activation function. In the experimental simulation section, the model is validated using real-world data. A comparison with four other typical models demonstrates that the proposed CBA model offers significant advantages in both recognition accuracy and robustness.
The increasing demand for edge computing requires effective Deep neuralnetwork (DNN) accelerators that are suitable for resource-limited environments. This paper presents a new method that uses distributed control me...
详细信息
ISBN:
(纸本)9798350387568;9798350387575
The increasing demand for edge computing requires effective Deep neuralnetwork (DNN) accelerators that are suitable for resource-limited environments. This paper presents a new method that uses distributed control methodology for DNN acceleration on edge devices. Our architecture offers significant improvements over a similar architecture without such feature, including a remarkable reduction in memory requirements by up to 7x, along with notable speedups of up to 7.42x in DNN processing. Additionally, our design reaches energy efficiency of a maximum of 4300 MOPS/W, demonstrating its potential to address resource constraints while improving DNN performance on edge platforms.
The removal of noise caused by environmental factors in microscopic imaging studies has become an important research topic in the field of medical imaging. In the medical imaging stage made with any digital microscopy...
详细信息
ISBN:
(数字)9781665450928
ISBN:
(纸本)9781665450935
The removal of noise caused by environmental factors in microscopic imaging studies has become an important research topic in the field of medical imaging. In the medical imaging stage made with any digital microscopy method (Confocal, Fluorescence, etc.), undesirable noises are added to the image obtained due to factors stemming from excessive or low illumination, high or low temperature, or electronic circuit equipment. The most basic noise model formed due to these environmental factors mentioned is the Gaussian normal distribution or a characteristic function close to this distribution. It is widely known that spatial filters (mean, median, Gaussian smoothing) are applied to eliminate Gaussian noise in digital image processing. However, undesirable results may occur in the images obtained when spatial filters are used to remove the noise in the images. In particular, because high frequencies are suppressed in images where spatial filters are applied, details are lost in the final image, and a blurred image is obtained. For this reason, four different convolutional neuralnetwork-based models are used for noise removal and to improve the PSNR values in this study. As a result, the modified U-Net improved the PSNR values for different noise levels as follows: +6.23, +7.88 and +10.52 dB
Natural Language processing (NLP) has undergone a remarkable transformation, with representation learning playing a pivotal role in reshaping the field. This review explores the evolution of NLP representation learnin...
详细信息
distributed acoustic sensors (DAS) are effective apparatuses that are widely used in many application areas for recording signals of various events with very high spatial resolution along optical fibers. To properly d...
详细信息
distributed acoustic sensors (DAS) are effective apparatuses that are widely used in many application areas for recording signals of various events with very high spatial resolution along optical fibers. To properly detect and recognize the recorded events, advanced signal processing algorithms with high computational demands are crucial. Convolutional neuralnetworks (CNNs) are highly capable tools to extract spatial information and are suitable for event recognition applications in DAS. Long short-term memory (LSTM) is an effective instrument to process sequential data. In this study, a two-stage feature extraction methodology that combines the capabilities of these neuralnetwork architectures with transfer learning is proposed to classify vibrations applied to an optical fiber by a piezoelectric transducer. First, the differential amplitude and phase information is extracted from the phasesensitive optical time domain reflectometer (40-OTDR) recordings and stored in a spatiotemporal data matrix. Then, a state-of-the-art pre-trained CNN without dense layers is used as a feature extractor in the first stage. In the second stage, LSTMs are used to further analyze the features extracted by the CNN. Finally, a dense layer is used to classify the extracted features. To observe the effect of different CNN architectures, the proposed model is tested with five state-of-the-art pre-trained models (VGG-16, ResNet-50, DenseNet-121, MobileNet, and Inception-v3). The results show that using the VGG-16 architecture in the proposed framework manages to obtain a 100% classification accuracy in 50 trainings and got the best results on the 40-OTDR dataset. The results of this study indicate that pre-trained CNNs combined with LSTM are very suitable to analyze differential amplitude and phase information represented in a spatiotemporal data matrix, which is promising for event recognition operations in DAS applications. (c) 2023 Optica Publishing Group
Background Cannabis is the most widely used illicit drug in the United States and is often associated with changes in attention function, which may ultimately impact numerous other cognitive faculties (e.g. memory, ex...
详细信息
Background Cannabis is the most widely used illicit drug in the United States and is often associated with changes in attention function, which may ultimately impact numerous other cognitive faculties (e.g. memory, executive function). Importantly, despite the increasing rates of cannabis use and widespread legalization in the United States, the neural mechanisms underlying attentional dysfunction in chronic users are poorly understood. Methods We used magnetoencephalography (MEG) and a modified Posner cueing task in 21 regular cannabis users and 32 demographically matched non-user controls. MEG data were imaged in the time-frequency domain using a beamformer and peak voxel time series were extracted to quantify the oscillatory dynamics underlying use-related aberrations in attentional reorienting, as well as the impact on spontaneous neural activity immediately preceding stimulus onset. Results Behavioral performance on the task (e.g. reaction time) was similar between regular cannabis users and non-user controls. However, the neural data indicated robust theta-band synchronizations across a distributednetwork during attentional reorienting, with activity in the bilateral inferior frontal gyri being markedly stronger in users relative to controls (p's < 0.036). Additionally, we observed significantly reduced spontaneous theta activity across this distributednetwork during the pre-stimulus baseline in cannabis users relative to controls (p's < 0.020). Conclusions Despite similar performance on the task, we observed specific alterations in the neural dynamics serving attentional reorienting in regular cannabis users compared to controls. These data suggest that regular cannabis users may employ compensatory processing in the prefrontal cortices to efficiently reorient their attention relative to non-user controls.
With the rapid advancement of distributed systems technology, deep learning-based methods have become a common scheme to implement multiple data processing. This paper presents a novel multi-channel encoder-decoder ar...
详细信息
The capacity of the brain to process input across temporal scales is exemplified in human narrative, which requires integration of information ranging from words, over sentences to long paragraphs. It has been shown t...
The capacity of the brain to process input across temporal scales is exemplified in human narrative, which requires integration of information ranging from words, over sentences to long paragraphs. It has been shown that this processing is distributed in a hierarchy across multiple areas in the brain with areas close to the sensory cortex, processing on a faster time scale than areas in associative cortex. In this study we used reservoir computing with human derived connectivity to investigate the effect of the structural connectivity on time scales across brain regions during a narrative task paradigm. We systematically tested the effect of removal of selected fibre bundles (IFO, ILF, MLF, SLF I/II/III, UF, AF) on the processing time scales across brain regions. We show that long distance pathways such as the IFO provide a form of shortcut whereby input driven activation in the visual cortex can directly impact distant frontal areas. To validate our model we demonstrated significant correlation of our predicted time scale ordering with empirical results from the intact/scrambled narrative fMRI task paradigm. This study emphasizes structural connectivity's role in brain temporal processing hierarchies, providing a framework for future research on structure and neural dynamics across cognitive tasks.
Most algorithms for decentralized learning employ a consensus or diffusion mechanism to drive agents to a common solution of a global optimization problem. Generally this takes the form of linear averaging, at a rate ...
详细信息
ISBN:
(纸本)9789464593617;9798331519773
Most algorithms for decentralized learning employ a consensus or diffusion mechanism to drive agents to a common solution of a global optimization problem. Generally this takes the form of linear averaging, at a rate of contraction determined by the mixing rate of the underlying network topology. For very sparse graphs this can yield a bottleneck, slowing down the convergence of the learning algorithm. We show that a sequence of matrices achieving finite-time consensus can be learned for unknown graph topologies in a decentralized manner by solving a constrained matrix factorization problem. We demonstrate numerically the benefit of the resulting scheme in both structured and unstructured graphs.
暂无评论