检索结果-内蒙古大学图书馆

An Explainable Deep Neural Network Model Based on Multi-Granularity Co-Attention to Improve Prediction of Drug-Target Binding Affinity

学校读者我要写书评

暂无评论

SSRN

SSRN 2024年

作者： Lin, Yanmei Cao, Aiqing Deng, Lei Liao, Mingzhi Zhang, Ru Zhang, Hao Peng, Yuzhong Guangxi Key Lab of Human-machine Interaction and Intelligent Decision Nanning Normal University Nanning530001 China Guangxi Academy of Sciences Nanning530007 China School of Computer Science and Engineering Central South University Changsha410083 China Center of Bioinformatics College of Life Sciences Northwest A&F University Shaanxi Yangling712100 China Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Shenzhen518000 China Center for Applied Mathematics of Guangxi Nanning Normal University Nanning530100 China

The prediction of drug-target interactions is pivotal in modern new drug development and drug repositioning. Nonetheless, current methods for predicting drug-target interactions often lose essential molecular structure information during the modeling process, leading to low prediction accuracy. This work proposes rMolGIN, a novel graph neural network with residual connectivity for molecular feature learning. rMolGIN not only takes into account the differences in chemical bonding properties and atomic neighborhood interactions, but also captures global and local structural information of drug molecules. Furthermore, we propose a novel drug-target affinity model based on rMolGIN and deep neural networks, coupled with a multi-granularity co-attention mechanism called HMCoDTA to capture comprehensive structural insights from both drugs and proteins. The proposed innovative model allows for comprehensive insight into the structural relationships between drugs and proteins, facilitating a more accurate prediction of binding affinities. To validate the effectiveness of our proposed methods, we conducted extensive experiments on three benchmark datasets of drug-target binding affinity, comparing HMCoDTA against 19 state-of-the-art models. Notably, the results show that HMCoDTA outperforms existing methods, demonstrating the effectiveness and advantages of our model in predicting drug-target binding affinity. © 2024, The Authors. All rights reserved.

关键词： Prediction models

Beamforming Design for the Performance Optimization of Intelligent Reflecting Surface Assisted Multicast MIMO Networks

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Zhang, Songling Yang, Zhaohui Chen, Mingzhe Liu, Danpu Wong, Kai-Kit Poor, H. Vincent The Beijing Laboratory of Advanced Information Network Beijing University of Posts and Telecommunications Beijing100876 China The College of Information Science and Electronic Engineering Zhejiang University Hangzhou310027 China Hangzhou310007 China Zhejiang Lab. Hangzhou31121 China The Department of Electrical and Computer Engineering Institute for Data Science and Computing University of Miami Coral GablesFL33146 United States The Department of Electronic and Electrical Engineering University College London LondonWC1E 6BT United Kingdom The Department of Electrical and Computer Engineering Princeton University PrincetonNJ08544 United States

In this paper, the problem of maximizing the sum of data rates of all users in an intelligent reflecting surface (IRS)-assisted millimeter wave multicast multiple-input multiple-output communication system is studied. In the considered model, one IRS is deployed to assist the communication from a multi-antenna base station (BS) to the multi-antenna users that are clustered into several groups. Our goal is to maximize the sum rate of all users by jointly optimizing the transmit beamforming matrices of the BS, the receive beamforming matrices of the users, and the phase shifts of the IRS. To solve this non-convex problem, we first use a block diagonalization method to represent the beamforming matrices of the BS and the users by the phase shifts of the IRS. Then, substituting the expressions of the beamforming matrices of the BS and the users, the original sum-rate maximization problem can be transformed into a problem that only needs to optimize the phase shifts of the IRS. To solve the transformed problem, a manifold method is used. Simulation results show that the proposed scheme can achieve up to 28.6% gain in terms of the sum rate of all users compared to the algorithm that optimizes the hybrid beamforming matrices of the BS and the users using our proposed scheme and randomly determines the phase shifts of the IRS. Copyright © 2022, The Authors. All rights reserved.

关键词： Multicasting

Expectation-maximization contrastive learning for compact video-and-language representations 22

学校读者我要写书评

暂无评论

Expectation-maximization contrastive learning for compact vi...

Proceedings of the 36th International Conference on Neural Information Processing Systems

作者： Peng Jin Jinfa Huang Fenglin Liu Xian Wu Shen Ge Guoli Song David A. Clifton Jie Chen School of Electronic and Computer Engineering Peking University China and AI for Science (AI4S)-Preferred Program Peking University Shenzhen Graduate School China Department of Engineering Science University of Oxford UK Tencent JARVIS Lab China Peng Cheng Laboratory Shenzhen China Department of Engineering Science University of Oxford UK and Oxford-Suzhou Centre for Advanced Research Suzhou China School of Electronic and Computer Engineering Peking University China and Peng Cheng Laboratory Shenzhen China and AI for Science (AI4S)-Preferred Program Peking University Shenzhen Graduate School China

ISBN: (纸本)9781713871088

Most video-and-language representation learning approaches employ contrastive learning, e.g., CLIP [53], to project the video and text features into a common latent space according to the semantic similarities of text-video pairs. However, such learned shared latent spaces are not often optimal, and the modality gap between visual and textual representation can not be fully eliminated. In this paper, we propose Expectation-Maximization Contrastive Learning (EMCL) to learn compact video-and-language representations. Specifically, we use the Expectation-Maximization algorithm to find a compact set of bases for the latent space, where the features could be concisely represented as the linear combinations of these bases. Such feature decomposition of video-and-language representations reduces the rank of the latent space, resulting in increased representing power for the semantics. Extensive experiments on three benchmark text-video retrieval datasets prove that our EMCL can learn more discriminative video-and-language representations than previous methods, and significantly outperform previous state-of-the-art methods across all metrics. More encouragingly, the proposed method can be applied to boost the performance of existing approaches either as a jointly training layer or an out-of-the-box inference module with no extra training, making it easy to be incorporated into any existing methods.

关键词：

Heart Disease Detection using Quantum Computing and Partitioned Random Forest Methods

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Heidari, Hanif Hellstern, Gerhard Murugappan, Murugappan School of Mathematics and Computer Science Damghan University Damghan Iran Center of Finance Cooperative State University Baden‐Württemberg Stuttgart Germany Research Lab Department of Electronics and Communication Engineering Kuwait College of Science and Technology Block 4 Doha13133 Kuwait Department of Electronics and Communication Engineering School of Engineering Vels Institute of Sciences Technology and Advanced Studies Chennai600117 India Universiti Malaysia Perlis Perlis Arau02600 Malaysia

Heart disease morbidity and mortality rates are increasing, which has a negative impact on public health and the global economy. Early detection of heart disease reduces the incidence of heart mortality and morbidity. Recent research has utilized quantum computing methods to predict heart disease with more than 5 qubits and are computationally intensive. Despite the higher number of qubits, earlier work reports a lower accuracy in predicting heart disease, have not considered the outlier effects, and requires more computation time and memory for heart disease prediction. To overcome these limitations, we propose hybrid random forest quantum neural network (HQRF) using a few qubits (two to four) and considered the effects of outlier in the dataset. Two open-source datasets, Cleveland and Statlog, are used in this study to apply quantum networks. The proposed algorithm has been applied on two open-source datasets and utilized two different types of testing strategies such as 10-fold cross validation and 70-30 train/test ratio. We compared the performance of our proposed methodology with our earlier algorithm called hybrid quantum neural network (HQNN) proposed in the literature for heart disease prediction. HQNN and HQRF outperform in 10-fold cross validation and 70/30 train/test split ratio, respectively. The results show that HQNN requires a large training dataset while HQRF is more appropriate for both large and small training dataset. According to the experimental results, the proposed HQRF is not sensitive to the outlier data compared to HQNN. Compared to earlier works, the proposed HQRF achieved a maximum area under the curve (AUC) of 96.43% and 97.78% in predicting heart diseases using Cleveland and Statlog datasets, respectively with HQNN. The proposed HQRF is highly efficient in detecting heart disease at an early stage and will speed up clinical *** Codes 92C50, 68P30, 68Q87, 68T20, 68Q12 © 2022, CC BY.

关键词： Forecasting

Gray Learning from Non-IID Data with Out-of-distribution Samples

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Zhao, Zhilin Cao, Longbing Wang, Chang-Dong The Data Science Lab School of Computing and DataX Research Centre Macquarie University SydneyNSW2109 Australia The School of Computer Science and Engineering Sun Yat-sen University Guangzhou China Guangdong Province Key Laboratory of Computational Science Guangzhou China Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education China

The integrity of training data, even when annotated by experts, is far from guaranteed, especially for non-IID datasets comprising both in- and out-of-distribution samples. In an ideal scenario, the majority of samples would be in-distribution, while samples that deviate semantically would be identified as out-of-distribution and excluded during the annotation process. However, experts may erroneously classify these out-of-distribution samples as in-distribution, assigning them labels that are inherently unreliable. This mixture of unreliable labels and varied data types makes the task of learning robust neural networks notably challenging. We observe that both in- and out-of-distribution samples can almost invariably be ruled out from belonging to certain classes, aside from those corresponding to unreliable ground-truth labels. This opens the possibility of utilizing reliable complementary labels that indicate the classes to which a sample does not belong. Guided by this insight, we introduce a novel approach, termed Gray Learning (GL), which leverages both ground-truth and complementary labels. Crucially, GL adaptively adjusts the loss weights for these two label types based on prediction confidence levels. By grounding our approach in statistical learning theory, we derive bounds for the generalization error, demonstrating that GL achieves tight constraints even in non-IID settings. Extensive experimental evaluations reveal that our method significantly outperforms alternative approaches grounded in robust statistics. Copyright © 2022, The Authors. All rights reserved.

关键词： Machine learning

Optical interface engineering with on-demand magnetic surface conductivities

学校读者我要写书评

暂无评论

Physical Review B 2022年第3期106卷 035304-035304页

作者： Yuhan Zhong Tong Cai Tony Low Hongsheng Chen Xiao Lin Interdisciplinary Center for Quantum Information State Key Laboratory of Modern Optical Instrumentation ZJU-Hangzhou Global Scientific and Technological Innovation Center College of Information Science and Electronic Engineering Zhejiang University Hangzhou 310027 China International Joint Innovation Center ZJU-UIUC Institute Key Lab. of Advanced Micro/Nano Electronic Devices & Smart Systems of Zhejiang The Electromagnetics Academy at Zhejiang University Zhejiang University Haining 314400 China Department of Electrical and Computer Engineering University of Minnesota Minneapolis Minnesota 55455 USA

Optical interfaces with arbitrary magnetic and electric surface conductivities can enable the design of photonic devices with new functionalities, but practical approaches to date are nonexistent. Regular interfaces, such as those with graphene, are optically interesting due to their tailorable electric surface conductivity. However, their magnetic surface conductivity is negligible since the magnetic response in natural materials is generally weak from the terahertz frequency onward. The quest for artificial magnetic response has recently triggered the development of magnetic metasurfaces that, however, can only provide the interface with a limited value of magnetic surface conductivity. Herein we find that vertical heterostructures based on regular nonmagnetic metasurfaces have a direct correspondence to an optical interface with both magnetic and electric surface conductivities, whose desired values can be structurally engineered. Moreover, we identify several unique photonic and plasmonic responses at optical interfaces with specific magnetic surface conductivities, including a polarization-insensitive Brewster effect and pure magnetic surface waves.

关键词： Electrical conductivity Electromagnetism Surface & interfacial phenomena Surface plasmons

An Asymmetric Modeling for Action Assessment 1

学校读者我要写书评

暂无评论

16th European Conference on computer Vision, ECCV 2020

作者： Gao, Jibin Zheng, Wei-Shi Pan, Jia-Hui Gao, Chengying Wang, Yaowei Zeng, Wei Lai, Jianhuang School of Data and Computer Science Sun Yat-sen University Guangzhou China Peng Cheng Laboratory Shenzhen518005 China School of Electronics Engineering and Computer Science Peking University Beijing China Pazhou Lab Guangzhou China Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education Guangzhou China

ISBN: (数字)9783030585778

ISBN: (纸本)9783030585761

Action assessment is a task of assessing the performance of an action. It is widely applicable to many real-world scenarios such as medical treatment and sporting events. However, existing methods for action assessment are mostly limited to individual actions, especially lacking modeling of the asymmetric relations among agents (e.g., between persons and objects);and this limitation undermines their ability to assess actions containingasymmetrically interactive motion patterns, since there always exists subordination between agents in many interactive actions. In this work, we model the asymmetric interactions among agents for action assessment. In particular, we propose an asymmetric interaction module (AIM), to explicitly model asymmetric interactions between intelligent agents within an action, where we group these agents into a primary one (e.g., human) and secondary ones (e.g., objects). We perform experiments on JIGSAWS dataset containing surgical actions, and additionally collect a new dataset, TASD-2, for interactive sporting actions. The experimental results on two interactive action datasets show the effectiveness of our model, and our method achieves state-of-the-art performance. The extended experiment on AQA-7 dataset also demonstrates the generalization capability of our framework to conventional action assessment. © 2020, Springer Nature Switzerland AG.

关键词： Intelligent agents

Twist-angle and thickness-ratio tuning of plasmon polaritons in twisted bilayer van der Waals films

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Wang, Chong Xie, Yuangang Ma, Junwei Hu, Guangwei Xing, Qiaoxia Huang, Shenyang Song, Chaoyu Wang, Fanjie Lei, Yuchen Zhang, Jiasheng Mu, Lei Zhang, Tan Huang, Yuan Qiu, Cheng-Wei Yao, Yugui Yan, Hugen School of Physics Beijing Institute of Technology Beijing100081 China Beijing Key Lab of Nanophotonics & Ultrafine Optoelectronic Systems School of Physics Beijing Institute of Technology Beijing100081 China Department of Physics Fudan University Shanghai200433 China Department of Electrical and Computer Engineering National University of Singapore Singapore117583 Singapore School of Electrical and Electronic Engineering Nanyang Technological University 50 Nanyang Avenue Singapore639798 Singapore Advanced Research Institute of Multidisciplinary Science Beijing Institute of Technology Beijing100081 China

Stacking bilayer structures is an efficient way to tune the topology of polaritons in in-plane anisotropic films, e.g., by leveraging the twist angle (TA). However, the effect of another geometric parameter, film thickness ratio (TR), on manipulating the plasmon topology in bilayers is elusive. Here, we fabricate bilayer structures of WTe2 films, which naturally host in-plane hyperbolic plasmons in the terahertz range. Plasmon topology is successfully modified by changing the TR and TA synergistically, manifested by the extinction spectra of unpatterned films and the polarization dependence of the plasmon intensity measured in skew ribbon arrays. Such TR- and TA-tunable topological transitions can be well explained based on the effective sheet optical conductivity by adding up those of the two films. Our study demonstrates TR as another degree of freedom for the manipulation of plasmonic topology in nanophotonics, exhibiting promising applications in bio-sensing, heat transfer and the enhancement of spontaneous emission. © 2023, CC BY.

关键词： Polariton

engineering synthetic gauge fields through the coupling phases in cavity magnonics

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Gardin, Alan Bourcin, Guillaume Bourhill, Jeremy Vlaminck, Vincent Person, Christian Fumeaux, Christophe Tettamanzi, Giuseppe C. Castel, Vincent School of Physics The University of Adelaide AdelaideSA5005 Australia IMT Atlantique Lab-STICC UMR CNRS 6285 BrestF-29238 France ARC Centre of Excellence for Engineered Quantum Systems ARC Centre of Excellence for Dark Matter Particle Physics Department of Physics University of Western Australia 35 Stirling Highway CrawleyWA6009 Australia School of Electrical Engineering and Computer Science The University of Queensland BrisbaneQLD4072 Australia School of Chemical Engineering and Advanced Materials The University of Adelaide AdelaideSA5005 Australia

Cavity magnonics, which studies the interaction of light with magnetic systems in a cavity, is a promising platform for quantum transducers and quantum memories. At microwave frequencies, the coupling between a cavity photon and a magnon, the quasi-particle of a spin wave excitation, is a consequence of the Zeeman interaction between the cavity’s magnetic field and the magnet’s macroscopic spin. For each photon/magnon interaction, a coupling phase factor exists, but is often neglected in simple systems. However, in "loop-coupled" systems, where there are at least as many couplings as modes, the coupling phases become relevant for the physics and lead to synthetic gauge fields. We present experimental evidence of the existence of such coupling phases by considering two spheres made of Yttrium-Iron-Garnet and two different re-entrant cavities. We predict numerically the values of the coupling phases, and we find good agreement between theory and the experimental data. These results show that in cavity magnonics, one can engineer synthetic gauge fields, which can be useful for cavity-mediated coupling and engineering dark mode physics. © 2023, CC BY-NC-SA.

关键词： Photons