Until recently, deep steganalyzers in spatial domain have been all designed for gray-scale images. In this paper, we propose WISERNet (the wider separate-then-reunion network) for steganalysis of color images. We prov...
详细信息
Considered the wireless sensor network clustering structure, a new big data collecting method based on compressive sensing is proposed. The collection process is as follows: in the cluster, the sink node sets the corr...
详细信息
Considered the wireless sensor network clustering structure, a new big data collecting method based on compressive sensing is proposed. The collection process is as follows: in the cluster, the sink node sets the corresponding seed vector based on the distribution of network, and then sends it to each cluster head. Cluster head can generate corresponding own random spacing sparse matrix based on its received seed vector, and collect data through compressive sensing technology; Among clusters, clusters forward measurement values to sink node along multi-hop routing tree which we built before. Performance analyzing and comparison of results show that this method is superior to other methods regardless of in a cluster or inter-cluster.
This paper proposes three methods to improve the learning algorithm for spiking neural networks（SNNs）. The aim is to improve learning performance in SNNs where neurons are allowed to fire multiple times. The perform...
详细信息
This paper proposes three methods to improve the learning algorithm for spiking neural networks（SNNs）. The aim is to improve learning performance in SNNs where neurons are allowed to fire multiple times. The performance is analyzed based on the convergence rate, the concussion condition in the training period and the error between actual output and desired output. The exclusive-or（XOR） and Wisconsin breast cancer（WBC） classification tasks are employed to validate the proposed optimized methods. Experimental results demonstrate that compared to original learning algorithm, all three methods have less iterations, higher accuracy, and more stable in the training period.
This paper proposed a chemical substance detection method using the Long Short-Term Memory of Recurrent Neural Networks(LSTM-RNN). The chemical substance data was collected using a mass spectrometer which is a time-se...
详细信息
This paper proposed a chemical substance detection method using the Long Short-Term Memory of Recurrent Neural Networks(LSTM-RNN). The chemical substance data was collected using a mass spectrometer which is a time-series data. The classification accuracy using the LSTM-RNN classifier is 96.84%, which is higher than 75.07% of the ordinary feed forward neural networks. The experimental results show that the LSTM-RNN can learn the properties of the chemical substance dataset and achieve a high detection accuracy.
This paper aims to develop a novel cost-effective framework for face identification, which progressively maintains a batch of classifiers with the increasing face images of different individuals. By naturally combinin...
详细信息
In embedded Internet of Things(IOT) environment, there are the troubles such as complex background, illumination changes, shadows and other factors for detecting moving object, so we put forward a new detection servic...
详细信息
In embedded Internet of Things(IOT) environment, there are the troubles such as complex background, illumination changes, shadows and other factors for detecting moving object, so we put forward a new detection service method through mixing Gaussian Mixture Model(GMM), edge detection service method and continuous frame difference method in this paper. In time domain, the new method uses GMM to model and updates the background. In spatial domain, it uses the hybrid detection service method which mixes edge detection service method, continuous frame difference method and GMM to get initial contour of moving object, and gets ultimate moving object. This method not only can well adapt to the illumination gradients and background disturbance occurred on scene, but also can well solve some problems such as inaccurate target detection, incomplete edge detection, cavitation and ghost which usually appears in traditional method. As experimental result showing, this method holds better real-time and robustness. It is not only easily implemented, but also can accurately detect moving object.
Simulation is an important technique for integrating interacting models for predicting results of hypothetical scenarios. A typical application area for simulators is virtual prototyping (VP). In VP, simulators replac...
详细信息
The precise prediction of bus routes or the arrival time of buses for a traveler can enhance the quality of bus service. However, many social factors influence people's preferences for taking buses. These social f...
详细信息
As smart phones with GPS become popular, more and more textual documents with geographical locations are published on the Web. Keyword-based location services like vehicle navigation, tour planning, nearby object quer...
详细信息
Many large-scale systems benefit from an organizational structure to provide for problem decomposition. A pivotal problem solving setting is given by hierarchical control systems familiar from hierarchical task networ...
详细信息
Many large-scale systems benefit from an organizational structure to provide for problem decomposition. A pivotal problem solving setting is given by hierarchical control systems familiar from hierarchical task networks. If these structures can be modified autonomously by, e.g., Coalition formation and reconfiguration, adequate decisions on higher levels require a faithful abstracted model of a collective of agents. An illustrative example is found in calculating schedules for a set of power plants organized in a hierarchy of Autonomous Virtual Power Plants. Functional dependencies over the combinatorial domain, such as the joint costs or rates of change of power production, are approximated by repeatedly sampling input-output pairs and substituting the actual functions by piecewise linear functions. However, if the sampled data points are weakly informative, the resulting abstracted high-level optimization introduces severe errors. Furthermore, obtaining additional point labels amounts to solving computationally hard optimization problems. Building on prior work, we propose to apply techniques from active learning to maximize the information gained by each additional point. Our results show that significantly better allocations in terms of cost-efficiency (up to 33.7 % reduction in costs in our case study) can be found with fewer but carefully selected sampling points using Decision Forests.
暂无评论