检索结果-内蒙古大学图书馆

Towards Precision Cancer Therapy: Prottrans and Multi-Window Scanning Convolutional Neural Networks Transforming Protein-Peptide Interaction Predictions

SSRN

引用

SSRN 2024年

作者： Van Le, The Zi Zhan, Jun Yu Ou, Yen Department of Computer Science and Engineering Yuan Ze University Chung-Li32003 Taiwan Graduate Program in Biomedical Informatics Yuan Ze University Chung-Li32003 Taiwan

This study delves into the prediction of protein-peptide interactions using advanced machine learning techniques, comparing models such as sequence-based, standard CNNs, and traditional classifiers. Leveraging pre-trained language models and multi-view window scanning CNNs, our approach yields significant improvements, with ProtTrans standing out based on 2.1 billion protein sequences and 393 billion amino acids. The integrated model achieves an impressive AUC of 0.855 and 0.822 on Set_1 and Set_2 datasets, outperforming previous methods. Beyond this, we explore the application of this model in cancer therapy, particularly in identifying peptide interactions for selective targeting of cancer cells. The findings of this study contribute to bioinformatics, providing valuable insights for drug discovery and therapeutic development. © 2024, The Authors. All rights reserved.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Symplectic discrete-time Krasovskii passivity-based control for output consensus*

引用

IFAC-PapersOnLine 2023年第2期56卷 8562-8567页

作者： Yu Kawano Alessio Moreschini Michele Cucuzzella Graduate School of Advanced Science and Engineering Hiroshima University Higashi-hiroshima 739-8527 Japan Department of Electrical and Electronic Engineering Imperial College London SW7 2AZ London U.K. Department of Electrical Computer and Biomedical Engineering University of Pavia 27100 Pavia Italy

In this paper, we design a sampled-data distributed output feedback controller to achieve output consensus for linear continuous-time port-Hamiltonian systems in presence of unknown disturbances. The key idea is borrowed from Krasovskii passivity-based output consensus control for continuous-time dynamics. To conceptualise this rationale to sampled control systems, we deal with a discrete-time system arising from a symplectic discretization of a continuous-time linear port-Hamiltonian system, such as the implicit midpoint method. As a preliminary step, we introduce the concept of Krasovskii passivity for discrete-time systems and further show that a discretized linear port-Hamiltonian system is Krasovskii passive in the discrete-time sense. Then, based on the discrete-time version of Krasovskii passivity, we develop a sampled-data output feedback controller to achieve output consensus. The proposed sampled-data controller can be understood as a symplectic discretization of the continuous-time output consensus controller. Finally, we illustrate the effectiveness of the main result by achieving current sharing in a DC power network.

关键词： Sampled-data control port-Hamiltonian systems passivity output consensus

来源：评论

学校读者我要写书评

暂无评论

Deepepiil13: Deep Learning for Prediction of Il-13 Inducing Epitopes Using Pre-Trained Language Models and Multi-Window Convolutional Neural Networks

SSRN

引用

SSRN 2024年

作者： Chuang, Cheng-Che Ou, Yu-Yen Department of Computer Science and Engineering Yuan Ze University Chung-Li32003 Taiwan Graduate Program in Biomedical Informatics Yuan Ze University Chung-Li32003 Taiwan

Interleukin-13 (IL-13) is a key cytokine involved in allergic inflammation and the cytokine storm associated with severe COVID-19. Identifying antigenic epitopes capable of inducing IL-13 holds therapeutic potential for developing epitope-based vaccines and immunomodulatory treatments. However, conventional methods for epitope prediction are often inefficient and inaccurate. This study presents DeepEpiIL13, a novel deep learning framework that integrates pre-trained language models and multi-window convolutional neural networks (CNNs) to rapidly and accurately predict IL-13-inducing epitopes from protein sequences. The ProtTrans pre-trained language model was employed to generate high-dimensional embeddings that capture rich contextual information from protein sequences. These embeddings were then inputted into a multi-window CNN architecture, enabling the efficient exploration of local and global sequence patterns associated with IL-13 induction. The proposed approach was rigorously evaluated using benchmark datasets and an independent SARS-CoV-2 dataset. DeepEpiIL13 achieved superior performance compared to traditional methods, with an impressive Matthews correlation coefficient (MCC) of 0.52 and an area under the receiver operating characteristic curve (AUC) of 0.86 on the benchmark dataset. On the independent SARS-CoV-2 dataset, DeepEpiIL13 demonstrated remarkable robustness, attaining an MCC of 0.63 and an AUC of 0.92, highlighting its potential applicability in the context of COVID-19 research. This study introduces a powerful deep learning framework for accurate epitope prediction, offering new avenues for the development of epitope-based vaccines and immunotherapies targeting IL-13-mediated disorders. The successful identification of IL-13-inducing epitopes paves the way for novel therapeutic interventions against allergic diseases, inflammatory conditions, and potentially severe viral infections like COVID-19. © 2024, The Authors. All rights reserved.

关键词： COVID-19

来源：评论

学校读者我要写书评

暂无评论

Composite Distributed Learning and Synchronization of Nonlinear Multi-Agent Systems with Complete Uncertain Dynamics

arXiv

引用

arXiv 2024年

作者： Jandaghi, Emadodin Stein, Dalton L. Hoburg, Adam Stegagno, Paolo Zhou, Mingxi Yuan, Chengzhi The Department of Mechanical Industrial and Systems Engineering KingstonRI02881 United States The Department of Electrical Computer and Biomedical Engineering KingstonRI02881 United States The Graduate School of Oceanography KingstonRI02881 United States

This paper addresses the problem of composite synchronization and learning control in a network of multiagent robotic manipulator systems with heterogeneous nonlinear uncertainties under a leader-follower framework. A novel two-layer distributed adaptive learning control strategy is introduced, comprising a first-layer distributed cooperative estimator and a second-layer decentralized deterministic learning controller. The first layer is to facilitate each robotic agent’s estimation of the leader’s information. The second layer is responsible for both controlling individual robot agents to track desired reference trajectories and accurately identifying/learning their nonlinear uncertain dynamics. The proposed distributed learning control scheme represents an advancement in the existing literature due to its ability to manage robotic agents with completely uncertain dynamics including uncertain mass matrices. This allows the robotic control to be environment-independent which can be used in various settings, from underwater to space where identifying system dynamics parameters is challenging. The stability and parameter convergence of the closed-loop system are rigorously analyzed using the Lyapunov method. Numerical simulations validate the effectiveness of the proposed scheme. © 2024, CC BY.

关键词： Lyapunov methods

来源：评论

学校读者我要写书评

暂无评论

Evaluating the Impact of Data Cleaning for Improving Road Damage Detection Through Vision Transformer

Evaluating the Impact of Data Cleaning for Improving Road Da...

引用

IEEE International Conference on Consumer Electronics (ICCE)

作者： Andy Desman Kahlil Muchtar Maulisa Oktiana Maya Fitria Yuwaldi Away Fardian Fardian Hammam Riza Dept. of Electrical and Computer Engineering Universitas Syiah Kuala Banda Aceh Indonesia Dept. of Electrical and Computer Engineering Department of Informatics Universitas Syiah Kuala The Master Program in Artificial Intelligence Universitas Syiah Kuala (USK) Banda Aceh Indonesia Department of Informatics BRIN (National Research and Innovation Agency) Indonesia The Master Program in Artificial Intelligence Universitas Syiah Kuala Banda Aceh Indonesia

ISBN: (数字)9798331521165

ISBN: (纸本)9798331521172

The WHO predicts that by 2030 road accidents will be the 5th leading cause of death. Globally, road accidents account for 1.25 million casualties each year, and road defects cause 34% of these casualties. The road survey process in many countries have several challenges, one of which is detection using cameras that do not have a recognition system. In this study, a model with YOLOS architecture based on Vision Transformer trained on the RDD2022 dataset successfully recognizes road damage well, as indicated by the number of objects detected, bounding box on accurate objects, and the ability to recognize objects with inconsistent shadow and light inference. This research uses assessment parameters such as Average Precision (AP) and Average Recall (AR) to determine the overall performance of the model. The model achieves the highest AP value at Intersection of Union (IoU) 0.5, 0.75, and 0.5-0.95, worth 62.1%, 37.1%, and 36.2% respectively, and the highest AR value in Large, Medium, and Small Areas, worth 42.1%, 60.3%, and 75.4% respectively. The supplementary material can be found through this link: https://***/watch?v=LzkI2e_IORE.

关键词： YOLO Surveys computer vision Road accidents Roads Manuals Transformers Cameras Cleaning Tuning

来源：评论

学校读者我要写书评

暂无评论

Fuzzy Support Vector Regression with Grey Wolf Optimization in Stock Market Prediction

Fuzzy Support Vector Regression with Grey Wolf Optimization ...

引用

International Conference on electrical engineering/Electronics, computer, Telecommunications and Information Technology, ECTI-CON

作者： Titimakan Sonsupap Sansanee Auephanwiriyakul Nipon Theera-Umpon Computer Engineering Department Faculty of Engineering Graduate School Chiang Mai University Chiang Mai Thailand Computer Engineering Department Faculty of Engineering Biomedical Engineering Institute Biomedical Engineering and Innovation Research Center Chiang Mai University Chiang Mai Thailand Electrical Engineering Department Faculty of Engineering Biomedical Engineering Institute Biomedical Engineering and Innovation Research Center Chiang Mai University Chiang Mai Thailand

ISBN: (数字)9798350381559

ISBN: (纸本)9798350381566

The stock market price is influenced by many factors both domestic and international factors. To help stock traders in make buying or selling decision, a stock price prediction model is needed. In this paper, a stock closing price prediction system is introduced. We utilized 17 financial factors, i.e., 8 technical analysis factors (Crude oil price, Gold spot, Thai Baht to US Dollar exchange rate, High price, Low price, Opening price, Closing price, and Volume) and 9 fundamental factors (Exponential moving average, Relative strength index, Current ratio, Return on equity ratio, Return on assets ratio, Net profit margin ratio, Debt to equity ratio, Price to earning ratio, and Price to book value) from 18 previous working days as our inputs. We then computed chaos centroids from each factor. Finally, to predict the Monday closing price, the fuzzy support vector regression with the grey wolf optimization is utilized. There are 29 companies in 6 industry groups, i.e., RESOURCE, SERVICE, INDUS, PROPCON, AGRO, and TECH, considered in this research. We found that the minimum root mean square error of the blind test set is 0.3698 and the maximum of that is 11.66. However, the prediction trend of each company is very similar to the real closing price.

关键词： Support vector machines Industries Gold Oils Companies Market research Indexes

来源：评论

学校读者我要写书评

暂无评论

Beyond Distribution Shift: Spurious Features Through the Lens of Training Dynamics

arXiv

引用

arXiv 2023年

作者： Murali, Nihal Puli, Aahlad Yu, Ke Ranganath, Rajesh Batmanghelich, Kayhan Intelligent Systems Program University of Pittsburgh United States Department of Computer Science New York University United States Department of Electrical and Computer Engineering Boston University United States

Deep Neural Networks (DNNs) are prone to learning spurious features that correlate with the label during training but are irrelevant to the learning problem. This hurts model generalization and poses problems when deploying them in safety-critical applications. This paper aims to better understand the effects of spurious features through the lens of the learning dynamics of the internal neurons during the training process. We make the following observations: (1) While previous works highlight the harmful effects of spurious features on the generalization ability of DNNs, we emphasize that not all spurious features are harmful. Spurious features can be "benign" or "harmful" depending on whether they are "harder" or "easier" to learn than the core features for a given model. This definition is model and dataset dependent. (2) We build upon this premise and use instance difficulty methods (like Prediction Depth (Baldock et al., 2021)) to quantify "easiness" for a given model and to identify this behavior during the training phase. (3) We empirically show that the harmful spurious features can be detected by observing the learning dynamics of the DNN’s early layers. In other words, easy features learned by the initial layers of a DNN early during the training can (potentially) hurt model generalization. We verify our claims on medical and vision datasets, both simulated and real, and justify the empirical success of our hypothesis by showing the theoretical connections between Prediction Depth and information-theoretic concepts like V-usable information (Ethayarajh et al., 2021). Lastly, our experiments show that monitoring only accuracy during training (as is common in machine learning pipelines) is insufficient to detect spurious features. We, therefore, highlight the need for monitoring early training dynamics using suitable instance difficulty metrics. © 2023, CC BY.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Enhancing the Throughput of Device-to-Device Communication in Cellular Systems Using Non-Orthogonal Transmission

引用

IEEE Access 2024年 12卷 112290-112307页

作者： Chu-Tung Liu Hsuan-Jung Su Hsien-Bo Tseng Jhe-Yi Lin Wei-Hsiang Wang Alan Shenghan Tsai Yasuhiro Takano Graduate Institute of Communication Engineering National Taiwan University Taipei Taiwan Department of Electrical Engineering National Taiwan University Taipei Taiwan MediaTek Inc. Hsinchu Taiwan Realtek Semiconductor Corp. Hsinchu Taiwan Department of Electrical and Computer Engineering University of Maryland College Park MD USA *** Inc. Sunnyvale CA USA Department of Information Systems Engineering Chitose Institute of Science and Technology Hokkaido Chitose Japan

Device-to-Device (D2D) communications facilitate direct data exchange between two devices, bypassing the necessity of routing through a central base station. This proximity-based communication offers advantages such as high data rates, low latency, reduced power consumption, and efficient frequency reuse. In the cellular spectrum, D2D operations encompass overlay D2D and underlay D2D. Overlay D2D allocates orthogonal radio resources to D2D and cellular users, resulting in inefficient frequency reuse. On the other hand, underlay D2D shares the same radio resources among D2D and cellular users, necessitating centralized coordination and extensive exchanges of channel and traffic information for effective interference management. To address the limitations of overlay and underlay D2D, we introduce a scheme that allows D2D users to simultaneously and non-orthogonally transmit both D2D and cellular signals. This approach resembles underlay D2D in terms of high frequency reuse but eliminates the need for centralized interference management. In this paper, we investigate various system design aspects based on this scheme, including power allocation, multiple-antenna extension, scheduling constraints, and different interference cancellation techniques. Incorporating a coordinated scheduling method, the proposed scheme enhances the sum rate of a conventional multiple-antenna overlay D2D system by 2.14 times, with only a negligible impact on the cellular communication rate. Furthermore, the proposed scheme improves the sum rate by up to 87% within conventional underlay D2D systems, all without the need for additional centralized coordination.

关键词： Device-to-device communication Resource management Interference cancellation Cellular networks Spectral efficiency Precoding Throughput MIMO communication

来源：评论

学校读者我要写书评

暂无评论

UAV weaknesses against deauthentication based hijacking attacks

UAV weaknesses against deauthentication based hijacking atta...

引用

International Symposium on Applied Machine Intelligence and Informatics (SAMI)

作者： Brúnó Krasnyánszki Sándor Tihamér Brassai András Németh Under Graduate Student in Computer Science Engineering Óbuda University Budapest Hungary Department of Electrical Engineering Sapientia Hungarian University of Transylvania Corunca Romania Department of Electronic Warfare National University of Public Service Budapest Hungary

Unmanned Aerial Vehicles (UAVs) and Unmanned Aerial Systems (UAS) are more important than ever before and we’re using it daily for agriculture, photo making, film industry, Search & Rescue, long range cable quality control, Geo Informatics, cartography, and state use (including border protection, disaster recovery and the military). Most of the UAV/UAS devices are using digital communication protocols nowadays, especially the IEEE 802.11 Wireless Local Area of Network for the cheaper and middle price UAV/UAS. Unfortunately, the protocols specified by the previously mentioned IEEE standard are vulnerable against some attacks. This research paper proposes a method that can interrupt the normal operation of the UAV/UAS that are using the IEEE 802.11 protocol and hijack the interrupted UAV/UAS permanently. For this method, deauthentication attack has been performed against the UAV/UASs. The attack vector is capable of denying the communication between the UAV and the control station. With sufficient prior knowledge it is possible to hijack the UAV that communicates on a 802.11 based protocol. Deauthentication based attacks are much more sophisticated than for example traditional electronic jamming, because the target can be precisely chosen and the attack will not interrupt other devices using the same communication method. The research has unfortunately some limitations in equipment, measurements conducted only in three different types of UAVs from three price categories, but in the future the authors would like to extend the range of UAVs. From this three UAVs two are hijackable by this method and the third should also be hijackable with some modifications. This research could be a base later for UAV/UAS counter measure systems for the safety of all of us.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Plug-and-Play DGTD Implementation for General Dispersive Media

A Plug-and-Play DGTD Implementation for General Dispersive M...

引用

Antennas and Propagation & USNC/URSI National Radio Science Meeting

作者： Tiago Vilela Lima Amorim Elson José Da Silva Fernando José Da Silva Moreira Fernando Lisboa Teixeira Graduate Program in Electrical Engineering Federal University of Minas Gerais Belo Horizonte Brazil Department of Electrical Engineering Federal University of Minas Gerais Belo Horizonte Brazil Department of Electronic Engineering Federal University of Minas Gerais Belo Horizonte Brazil ElectroScience Laboratory The Ohio State University Columbus USA

ISBN: (数字)9798350369908

ISBN: (纸本)9798350369915

A discontinuous Galerkin implementation is presented for accurately calculating the electromagnetic scattering by general dielectric dispersive media in the time domain. To validate the formulation, the two-dimensional scattering of a TMz plane wave by a single pole Lorentz dispersive cylinder has been analyzed. The Fourier transform of the numerical solution in the time domain was compared with the analytical solution in the frequency domain at a given frequency. The results obtained are in agreement with the analytical solution.

关键词： Time-frequency analysis Fourier transforms Conferences Electromagnetic scattering Media Dielectrics Time-domain analysis Dispersion Method of moments Standards

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：