The deployment of mobile-Small cells (mScs) is widely adopted to intensify the quality-of-service (QoS) in high mobility vehicles. However, the rapidly varying interference patterns among densely deployed mScs make th...
详细信息
In distributed algorithms, multiple processing nodes collab.rate to achieve a common objective. One such algorithm, the Diffusion Least Mean Square (DLMS), is widely utilized across various applications due to its rel...
详细信息
In distributed algorithms, multiple processing nodes collab.rate to achieve a common objective. One such algorithm, the Diffusion Least Mean Square (DLMS), is widely utilized across various applications due to its reliability, robustness, and fast convergence. However, the presence of masked measurements can significantly limit the effectiveness of these algorithms. To address this challenge, this paper presents a comprehensive framework designed to mitigate masking effects while also analyzing the convergence of diffusion strategies. Accordingly, we modify the cost function to promote data exchange among estimator nodes, enhancing data flow across the network and improving the estimation of masked components. We demonstrate how the gradient noise in stochastic gradient descent can be bounded to ensure it grows no faster than the estimation error. The proposed approach is grounded in the minimum disturbance principle and is specifically crafted to counteract the adverse effects of impulsive noise. Our findings show that the proposed method significantly outperforms conventional DLMS approaches in scenarios with masked measurements, improving performance by over 40 dB compared to the standard DLMS and by over 20 dB compared to Mask-aware DLMS in terms of Mean Square Deviation (MSD). This advancement promises enhanced performance and reliability in challenging environments.
Modern musical source separation systems based on deep neural networks reach unprecedented levels of separation quality. However, harnessing the power of these large-scale models in typical audio production environmen...
ISBN:
(数字)9781509066315
ISBN:
(纸本)9781509066322
Modern musical source separation systems based on deep neural networks reach unprecedented levels of separation quality. However, harnessing the power of these large-scale models in typical audio production environments, which frequently offer only limited computing resources while demanding real-time processing, remains challenging. We extend the multi-scaled DenseNet in several aspects to facilitate real-time source separation scenarios. Specifically, we reduce the computational requirements by inferring Mel-scaled masks and decrease the model size via effective use of bottleneck layers, while improving performance using a deep clustering objective. In addition, we are able to further increase the model efficiency by applying parameterized structured pruning of convolutional weights without any significant impact on the separation performance. We significantly reduce the model size and increase the computational efficiency by a factor of 1.6 and 4.3, respectively, while maintaining the separation performance.
Determining the functional roles of proteins is a vital task to understand life at molecular level and has great biomedical and pharmaceutical implications. With the development of novel high-throughput techniques, en...
详细信息
Due to the limitation of hardware resources, the traditional people flow monitoring system based on computer vision in public places can't meet different crowd-scale scenarios. Therefore, a people flow monitoring ...
详细信息
The mobile robot adapts to the more complicated indoor and outdoor environments, and can expand its scope of application. In order to reduce the influence of the cumulative error caused by navigation in complex enviro...
详细信息
This paper presents a robust deep learning framework developed to detect respiratory diseases from recordings of respiratory sounds. The complete detection process firstly involves front end feature extraction where r...
详细信息
Errors in semantic segmentation could be classified into two types: the large area misclassification and inaccurate local boundaries. Previously attention-based methods typically capture rich global contextual informa...
详细信息
Errors in semantic segmentation could be classified into two types: the large area misclassification and inaccurate local boundaries. Previously attention-based methods typically capture rich global contextual information, which benefits the large area classification but cannot address the local errors of boundaries. In this paper, we propose a Global-Local Attention Network (GLANet) which can simultaneously consider the global context and local details. Specifically, our GLANet consists of two branches: (1) the global attention branch and (2) local attention branch. Furthermore, three different modules are embedded in GLANet for respectively modelling the semantic interdependencies in spatial, channel and boundary dimension. Lastly, we merge the outputs of different branches to enhance the feature representation further, resulting in more precise segmentation. Overall, the proposed method achieves the competitive segmentation accuracy on two public aerial image datasets, bringing significant improvements over the existing baselines.
Automated Depression Detection (ADD) in speech aims to automatically estimate one's depressive attributes through artificial intelligence tools towards spoken signals. Nevertheless, existing speech-based ADD works...
详细信息
Automated Depression Detection (ADD) in speech aims to automatically estimate one's depressive attributes through artificial intelligence tools towards spoken signals. Nevertheless, existing speech-based ADD works fail to sufficiently consider weakly-supervised cases with inaccurate lab.ls, which may typically appear in intelligent mental health. In this regard, we propose the Self-Learning-based lab.l Correction (SLLC) approach for weakly-supervised depression detection in speech. The proposed approach employs a self-learning manner connecting a lab.l correction module and a depression detection module. Within the approach, the lab.l correction module fuses likelihood-ratio-based and prototype-based lab.l correction strategies in order to effectively correct the inaccurate lab.ls, while the depression detection module aims at detecting depressed samples through a 1D convolutional recurrent neural network with multiple types of losses. The experimental results on two depression detection corpora show that our proposed SLLC approach performs better compared with existing state-of-the-art speech-based depression detection approaches, in the case of weak supervision with inaccurate lab.ls for depression detection in speech.
This paper presents a new method for segmenting medical images is based on Hamiltonian quaternions and the associative algebra, method of the active contour model and LPA-ICI (local polynomial approximation - the inte...
详细信息
暂无评论