Topic drift is a common phenomenon in multi-turn dialogue. Therefore, an ideal dialogue generation models should be able to capture the topic information of each context, detect the relevant context, and produce appro...
详细信息
Even though the RNN, LSTM, and other networks are used to extract dependencies in time series, sensor-based human behavior recognition (HAR) still faces some difficulties, and the ability of deep learning (DL) network...
详细信息
A series of surrogate-assisted evolutionary algorithms (SAEAs) have been proposed for expensive multi-objective optimization problems (EMOPs), building cheap surrogate models to replace the expensive real function eva...
详细信息
A series of surrogate-assisted evolutionary algorithms (SAEAs) have been proposed for expensive multi-objective optimization problems (EMOPs), building cheap surrogate models to replace the expensive real function evaluations. However, the search efficiency of these SAEAs is not yet satisfactory. More efforts are needed to further exploit useful information from the real function evaluations in order to better guide the search process. Facing this challenge, this paper proposes a Hyperbolic Neural network (HNN) based preselection operator to accelerate the optimization process based on limited evaluated solutions. First, the preselection task is modeled as a multi-label classification problem where solutions are classified into different layers (ordinal categories) through -relaxed objective aggregation. Second, in order to resemble the hierarchical structure of candidate solutions, a hyperbolic neural network is applied to tackle the multi-label classification problem. The reason for using HNN is that hyperbolic spaces more closely resemble hierarchical structures than Euclidean spaces. Moreover, to alleviate the data deficiency issue, a data augmentation strategy is employed for training the HNN. In order to evaluate its performance, the proposed HNN-based preselection operator is embedded into two surrogate-assisted evolutionary algorithms. Experimental results on two benchmark test suites and three real-world problems with up to 11 objectives and 150 decision variables involving seven state-of-the-art algorithms demonstrate the effectiveness of the proposed method. IEEE
We study the coexistence of energy-time entanglement with fiber-optical communication in the telecom C band. The property of noise from wavelength-multiplexed classical channels is characterized with different wavelen...
详细信息
We study the coexistence of energy-time entanglement with fiber-optical communication in the telecom C band. The property of noise from wavelength-multiplexed classical channels is characterized with different wavelength settings. With the largest noise, i.e., the worst case, we measure the entanglement property of the distributed energy-time entangled photon pairs at different data rates of fiber-optical communication. After being distributed over 40-km spooled fiber coexisting with a bidirectional data rate of 20 Gbps, a visibility of 82.01±1.10% is obtained by measuring the Franson interference. With the Bennett-Brassard-Mermin 1992 (BBM92) protocol, a secret key rate of 343 bits per second is reached over the 40-km spooled fiber coexisting with a bidirectional data rate of 10 Gbps. Our result paves the way for developing a cost-effective quantum entanglement network compatible with fiber communication systems.
Recent advances in stroke rehabilitation technology have been focused on developing Intelligent Rehabilitation Robots (IRR) that can effectively engage post-stroke patients (PSP) in intuitive motor training for full f...
详细信息
ISBN:
(数字)9798350371499
ISBN:
(纸本)9798350371505
Recent advances in stroke rehabilitation technology have been focused on developing Intelligent Rehabilitation Robots (IRR) that can effectively engage post-stroke patients (PSP) in intuitive motor training for full function recovery. Most existing rehabilitation robots incorporate functionalities that are passive in nature, constraining PSP to predetermined trajectories that often deviate from patients’ limb movement intentions, consequently hindering recovery. To resolve this issue, a robust deep-transfer learning driven network (DTLN) is developed to adequately characterize PSP’s motion intention signatures from neural oscillations towards achieving intuitive and active training. Thus, we investigated and proposed the utilization of mu-frequency spectrum (muFS) based CWT approach for Scalograms construction, which serves as inputs to the DTLN model that characterizes multiple classes of PSP’s motor execution signatures from multi-channel electroencephalography (EEG) recordings. Then, we evaluated the proposed method using EEG data from six PSP and compared the decoding results to those of related approaches under similar experimental settings. The proposed method resulted in a significant increment of 10.84 % - 13.19% decoding accuracy across stroke patients and better convergence in comparison to other methods. Additionally, the method exhibited distinct task separability for individual motor execution signature across patients. In conclusion, our method offers a consistently accurate decoding of motor tasks that could enable intuitively active robotic training in PSPs with impaired motor function.
Diffusion models are initially designed for image generation. Recent research shows that the internal signals within their backbones, named activations, can also serve as dense features for various discriminative task...
详细信息
Aiming at the problem of workflow scheduling under the "container virtual machine" two-tier structure in cloud microservice workflow application, a "container virtual machine" load balancing strate...
详细信息
作者:
Du, SichunZhu, HaodiZhang, YangHong, QinghuiHunan University
College of Computer Science and Electronic Engineering Changsha418002 China Shenzhen University
Computer Vision Institute School of Computer Science and Software Engineering National Engineering Laboratory for Big Data System Computing Technology Guangdong Key Laboratory of Intelligent Information Processing Shenzhen518060 China
Address event representation (AER) object recognition task has attracted extensive attention in neuromorphic vision processing. The spike-based and event-driven computation inherent in the spiking neural network (SNN)...
详细信息
This paper presents a novel controller design for dealing with the challenges posed by Denial-of-Service (DoS) attacks in the context of Artificial Intelligence of Things (AIOT). The proposed design employs a predicti...
详细信息
Embedding-based evaluation measures have shown promising improvements on the correlation with human judgments in natural language generation. In these measures, various intrinsic metrics are used in the computation, i...
详细信息
暂无评论