This paper proposes a novel method for on-line recognition of line-based graphic symbol. The input strokes are usually warped into a cursive form due to the sundry drawing style, and classifying them is very difficult...
详细信息
ISBN:
(纸本)0819442836
This paper proposes a novel method for on-line recognition of line-based graphic symbol. The input strokes are usually warped into a cursive form due to the sundry drawing style, and classifying them is very difficult. To deal with this, an ART-2 neuralnetwork is used to classify the input strokes. It has the advantages of high recognition rate, less recognition time and forming classes in a self-organized manner. The symbol recognition is achieved by an Attribute Relational Graph (ARG) matching algorithm. The ARG is very efficient for representing complex objects, but computation cost is very high. To over come this, we suggest a fast graph matching algorithm using symbol structure information. The experimental results show that the proposed method is effective for recognition of symbols Bath hierarchical structure.
This paper focuses on designing an adaptive controller for controlling traffic signal timing. Urban traffic is an inevitable part in modern cities and traffic signal controllers are effective tools to control it. In t...
详细信息
ISBN:
(纸本)9783319265353;9783319265346
This paper focuses on designing an adaptive controller for controlling traffic signal timing. Urban traffic is an inevitable part in modern cities and traffic signal controllers are effective tools to control it. In this regard, this paper proposes a distributedneuralnetwork (NN) controller for traffic signal timing. This controller applies cuckoo search (CS) optimization methods to find the optimal parameters in design of an adaptive traffic signal timing control system. The evaluation of the performance of the designed controller is done in a multi-intersection traffic network. The developed controller shows a promising improvement in reducing travel delay time compared to traditional fixed-time control systems.
An artificial neuralnetwork (ANN) is a parallel, distributedprocessing system consisting of a large number of interconnected neurons. At present, artificial neuralnetworks have been widely used in signal processing...
详细信息
ISBN:
(纸本)9781538644416
An artificial neuralnetwork (ANN) is a parallel, distributedprocessing system consisting of a large number of interconnected neurons. At present, artificial neuralnetworks have been widely used in signal processing, automation, control systems, image recognition and many other fields. Usually, the realization of neuralnetworks is based on software. However, because the software implementation method cannot achieve real-time calculation in many cases, the hardware implementation method can reflect the inherent parallel processing characteristics of neuralnetworks. This paper proposes an ANN neuralnetwork field programmable neuron array based on the design of reusable ANN artificial neuralnetwork IP core. It not only can save a lot of hardware resources and improve processing speed, but also has a rapid development cycle and good reconfigurability and other advantages.
An approach to the control of a distributed Solar Collector field relying on a non-linear adaptive constrained model-based predictive control scheme with steady-state offset compensation is developed and implemented. ...
详细信息
ISBN:
(纸本)0780377028
An approach to the control of a distributed Solar Collector field relying on a non-linear adaptive constrained model-based predictive control scheme with steady-state offset compensation is developed and implemented. This methodology is based on a non-linear state-space neuralnetworks within a model-based predictive control framework. The neuralnetwork training is carried out online by means of a distribution approximation filter approach. In order to get rid of static offsets an offset compensator is incorporated in the control loop. Tests on the ACUREX field illustrate the feasibility of the proposed approach.
In this paper, we provided a new technique based on the concept of comparison. Different from the Lyapunov method, the new technique showed that if the given conditions hold then the any state of neuralnetworks with ...
详细信息
ISBN:
(纸本)3540464794
In this paper, we provided a new technique based on the concept of comparison. Different from the Lyapunov method, the new technique showed that if the given conditions hold then the any state of neuralnetworks with distributed time delays and strongly nonlinear activation functions is always bounded by exponential convergence function. In addition, some sufficient conditions are obtained to guarantee that such neuralnetwork is globally exponentially stable, or locally exponentially stable. Furthermore, we obtained the estimates of the exponential convergence rates and the region of exponential convergence.
Recent progress on end-to-end neural diarization (EEND) has enabled overlap-aware speaker diarization with a single neuralnetwork. This paper proposes to enhance EEND by using multi-channel signals from distributed m...
详细信息
ISBN:
(纸本)9781665405409
Recent progress on end-to-end neural diarization (EEND) has enabled overlap-aware speaker diarization with a single neuralnetwork. This paper proposes to enhance EEND by using multi-channel signals from distributed microphones. We replace Transformer encoders in EEND with two types of encoders that process a multichannel input: spatio-temporal and co-attention encoders. Both are independent of the number and geometry of microphones and suitable for distributed microphone settings. We also propose a model adaptation method using only single-channel recordings. With simulated and real-recorded datasets, we demonstrated that the proposed method outperformed conventional EEND when a multi-channel input was given while maintaining comparable performance with a single-channel input. We also showed that the proposed method performed well even when spatial information is inoperative given multi-channel inputs, such as in hybrid meetings in which the utterances of multiple remote participants are played back from the same loudspeaker.
distributed inference techniques can be broadly classified into data-distributed and model-distributed schemes. In data-distributed inference (DDI), each worker carries the entire deep neuralnetwork (DNN) model, but ...
详细信息
ISBN:
(纸本)9798350302615
distributed inference techniques can be broadly classified into data-distributed and model-distributed schemes. In data-distributed inference (DDI), each worker carries the entire deep neuralnetwork (DNN) model, but processes only a subset of the data. However, feeding the data to workers results in high communication costs especially when the data is large. An emerging paradigm is model-distributed inference (MDI), where each worker carries only a subset of DNN layers. In MDI, a source device that has data processes a few layers of DNN and sends the output to a neighboring device. This process ends when all layers are processed in a distributed manner. In this paper, we investigate MDI with multiple sources, i.e., when more than one device has data. We design a multi-source MDI (MS-MDI), which optimizes task scheduling decisions across multiple source devices and workers. Experimental results on a real-life testbed of NVIDIA Jetson TX2 edge devices show that MS-MDI improves the inference time significantly as compared to baselines.
The visual simulation of neuronal activities was studied using the Hodgkin-Huxley equation. The complicated interaction between nerve cells from microscopic and macroscopic views were investigated employing parallel-d...
详细信息
The visual simulation of neuronal activities was studied using the Hodgkin-Huxley equation. The complicated interaction between nerve cells from microscopic and macroscopic views were investigated employing parallel-distributedprocessing and cellular automation concepts. A constructive method that simulates the spatial and temporal features of nerve cell excitement is proposed.
Y Sky computing is a new computing paradigm leveraging resources of multiple Cloud providers to create a large scale distributed infrastructure. N2Sky is a research initiative promising a framework for the utilization...
详细信息
ISBN:
(纸本)9783030042240;9783030042233
Y Sky computing is a new computing paradigm leveraging resources of multiple Cloud providers to create a large scale distributed infrastructure. N2Sky is a research initiative promising a framework for the utilization of neuralnetworks as services across many Clouds. This involves a number of challenges ranging from the provision, discovery and utilization of services to the management, monitoring, metering and accounting of the infrastructure. Cloud Container technology offers fast deployment, good portability, and high resource efficiency to run large-scale and distributed systems. In recent years, container-based virtualization for applications has gained immense popularity. This paper presents the new N2SkyC system, a framework for the utilization of neuralnetworks as services, aiming for higher flexibility, portability, dynamic orchestration, and performance by fostering microservices and Cloud container technology.
distributed scheduling algorithms for throughput or utility maximization in dense wireless multi-hop networks can have overwhelmingly high overhead, causing increased congestion, energy consumption, radio footprint, a...
详细信息
ISBN:
(纸本)9781665405409
distributed scheduling algorithms for throughput or utility maximization in dense wireless multi-hop networks can have overwhelmingly high overhead, causing increased congestion, energy consumption, radio footprint, and security vulnerability. For wireless networks with dense connectivity, we propose a distributed scheme for link sparsification with graph convolutional networks (GCNs), which can reduce the scheduling overhead while keeping most of the network capacity. In a nutshell, a trainable GCN module generates node embeddings as topology-aware and reusable parameters for a local decision mechanism, based on which a link can withdraw itself from the scheduling contention if it is not likely to win. In mediumsized wireless networks, our proposed sparse scheduler beats classical threshold-based sparsification policies by retaining almost 70% of the total capacity achieved by a distributed greedy max-weight scheduler with 0.4% of the point-to-point message complexity and 2.6% of the average number of interfering neighbors per link.
暂无评论