An investigation on the impact and significance of the AlphaGo vs. Lee Sedol Go match is conducted, and concludes with a conjecture of the AlphaGo Thesis and its extension in accordance with the Church-Turing Thesis i...
详细信息
Realizing the Ocean Internet of Things (OIoT) requires diverse and comprehensive real-time marine data. This creates significant demands on spectrum resources for effective underwater communication. Coexisting users i...
详细信息
Realizing the Ocean Internet of Things (OIoT) requires diverse and comprehensive real-time marine data. This creates significant demands on spectrum resources for effective underwater communication. Coexisting users in the OIoT can generate massive amounts of data, which results in competition for underwater acoustic spectrum. To address the problem of poor utilization of this spectrum in complex and dynamic ocean environments, this paper proposes an intelligent spectrum sensing scheme based on multimodal data fusion. First, the system obtains time series data for the underwater acoustic signals and a wavelet transform is used to obtain the corresponding image data. The time series and image data constitute multimodal data that provide a more comprehensive time and space perspective and improve the diversity of features. Then, unsupervised learning with a Denoising Autoencoder is used to extract high-quality features from the time series data. Finally, a parallel dual Backbone YOLO network is constructed to compensate for the inability of traditional YOLO to extract multimodal features. One branch captures key temporal features through a network built with deep separable convolutions, while the other branch captures key spatial features using an improved CSPDarknet. This Mul-YOLO network can extract hierarchical structure information from underwater acoustic signals and integrate the diverse multilevel features of the data to achieve accurate spectrum sensing. Compared with Convolutional Neural Network (CNN), ResNet, Swin-Transformer, ConvNext and YOLOv5 algorithms, the average detection probability of the Mul-YOLO algorithm is increased by about 5.9% to 18.9%, and the average false alarm probability is optimized by about 7% to 12.7% in the range of signal-to-noise ratio from −12 dB to 0 dB. The results given show that the proposed algorithm can detect spectrum holes with high accuracy and effectively avoid interference between users.
In this article, a compressive sensing-based reconstruction algorithm is applied to data acquired from a nodding multibeam Lidar system following a Lissajous-like trajectory. Multibeam Lidar systems provide 3D depth i...
详细信息
Achieving global asymptotic stabilization of rigid-body attitude is impossible using smooth feedback due to topological obstructions. In this paper, we propose a hybrid feedback that coordinates a "synergistic&qu...
详细信息
The rapid growth of the Internet and increased desmand to use the Internet for voice and video applications necessitate the design and utilization of new Internet architectures with effective congestion control algori...
详细信息
This paper considers the problem of approximating the infinite-horizon value function of the discrete-time switched LQR *** particular,the authors propose a new value iteration method to generate a sequence of monoton...
详细信息
This paper considers the problem of approximating the infinite-horizon value function of the discrete-time switched LQR *** particular,the authors propose a new value iteration method to generate a sequence of monotonically decreasing functions that converges exponentially to the value *** method facilitates us to use coarse approximations resulting from faster but less accurate algorithms for further value iteration,and thus,the proposed approach is capable of achieving a better approximation for a given computation time compared with the existing *** numerical examples are presented in this paper to illustrate the effectiveness of the proposed method.
Achieving global asymptotic stabilization of rigid-body attitude is impossible using smooth feedback;however, this obstruction can be overcome using a hybrid controller that coordinates a "synergistic" famil...
详细信息
This paper addresses the computation of the L2-induced gain for switched linear systems. The main contribution of the paper is to completely characterize the induced gain of a switched system though a differential ine...
详细信息
Recent demand and interest in wireless, mobile-based healthcare has driven significant interest towards developing alternative biopotential electrodes for patient physiological monitoring. The conventional wet adhesiv...
详细信息
Information search and retrieval from online sources or social forums is often performed with term based boolean queries. Such queries can produce low relevance documents in situations where the user is interested in ...
详细信息
暂无评论