检索结果-内蒙古大学图书馆

Integrative approach for predicting drug-target interactions via matrix factorization and broad learning systems

Mathematical Biosciences and engineering 2024年第2期21卷 2608-2625页

作者： Xu, Wanying Yang, Xixin Guan, Yuanlin Cheng, Xiaoqing Wang, Yu College of Computer Science & Technology Qingdao University Qingdao266071 China School of Automation Qingdao University Qingdao266071 China Key Lab of Industrial Fluid Energy Conservation and Pollution Control Ministry of Education Qingdao University of Technology Qingdao266520 China School of Mechanical & Automotive Engineering Qingdao University of Technology Qingdao266520 China

In the drug discovery process, time and costs are the most typical problems resulting from the experimental screening of drug-target interactions (DTIs). To address these limitations, many computational methods have been developed to achieve more accurate predictions. However, identifying DTIs mostly rely on separate learning tasks with drug and target features that neglect interaction representation between drugs and target. In addition, the lack of these relationships may lead to a greatly impaired performance on the prediction of DTIs. Aiming at capturing comprehensive drug-target representations and simplifying the network structure, we propose an integrative approach with a convolution broad learning system for the DTI prediction (ConvBLS-DTI) to reduce the impact of the data sparsity and incompleteness. First, given the lack of known interactions for the drug and target, the weighted K-nearest known neighbors (WKNKN) method was used as a preprocessing strategy for unknown drug-target pairs. Second, a neighborhood regularized logistic matrix factorization (NRLMF) was applied to extract features of updated drug-target interaction information, which focused more on the known interaction pair parties. Then, a broad learning network incorporating a convolutional neural network was established to predict DTIs, which can make classification more effective using a different perspective. Finally, based on the four benchmark datasets in three scenarios, the ConvBLS-DTI’s overall performance out-performed some mainstream methods. The test results demonstrate that our model achieves improved prediction effect on the area under the receiver operating characteristic curve and the precision-recall curve. ©2024 the Author(s), licensee AIMS Press. This is an open access article distributed under the terms of the Creative Commons Attribution License (http://***/licenses/by/4.0)

关键词： Learning systems

来源：评论

学校读者我要写书评

暂无评论

SpotMon: Enabling General Hotspot Monitoring in Key-Value Stores

SpotMon: Enabling General Hotspot Monitoring in Key-Value St...

引用

International Conference on Network Protocols

作者： Zhengyan Zhou Jinhan Zu Enhao Huang Zizhao Wang Haifeng Zhou Dong Zhang Xiang Chen Chunming Wu College of Computer Science and Technology Zhejiang University Quan Cheng Laboratory College of Control Science and Engineering Zhejiang University College of Computer and Data Science Fuzhou University Zhicheng College Fuzhou University

ISBN: (数字)9798350351712

ISBN: (纸本)9798350351729

Key-value stores are essential to online services such as e-commerce. In key-value stores, a hotspot (i.e., frequently accessed items) may cause severe load imbalances, high response latency, and Service Level Agreement (SLA) violations. However, existing works only focus on specific types of hotspots, thus overlooking other types of hotspots and leading to blind spots. In this paper, we propose SpotMon, a system that enables general hotspot monitoring in key-value stores. Specifically, we (1) systematically identify the generality requirements of hotspot monitoring from existing works, (2) formulate general hotspot monitoring as an arbitrary partial spot query problem, (3) measure the hotness of hotspot candidates with a new vector expression, (4) propose hotspot encoding, filtering, decoding, and querying to support general queries without focusing on specific hotspots, (5) leverage the in-network visibility of programmable switches to identify system-wide hotspots. Our extensive experiments indicate that SpotMon provides high accuracy (e.g., F1 score from 0.88 to 1) and enables efficient hotspot mitigations (e.g., up to $4.03 \times$ MQPS).

关键词： Accuracy Protocols Filtering Prevention and mitigation Focusing Encoding Vectors Decoding Monitoring Service level agreements

来源：评论

学校读者我要写书评

暂无评论

Modeling and Simulation of Two Axes Gimbal Using Fuzzy control

引用

computers, Materials & Continua 2022年第7期72卷 93-107页

作者： Ayman A.Aly Mohamed O.Elhabib Bassem F.Felemban B.Saleh Dac-Nhuong Le Department of Mechanical Engineering College of EngineeringTaif UniversityTaif21944Saudi Arabia Control and Mechatronics Division School of Electrical EngineeringUTMJohor Bahru81300Malaysia Institute of Research and Development Duy Tan UniversityDanang550000Vietnam School of Computer Science Duy Tan UniversityDanang550000Vietnam

The application of the guided missile seeker is to provide stability to the sensor’s line of sight toward a target by isolating it from the missile motion and *** main objective of this paper is not only to present the physical modeling of two axes gimbal system but also to improve its performance through using fuzzy logic controlling *** paper is started by deriving the mathematical model for gimbals motion using Newton’s second law,followed by designing the mechanical parts of model using SOLIDWORKS and converted to xml file to connect dc motors and sensors using MATLAB/***,a Mamdani-type fuzzy and a Proportional-Integral-Derivative(PID)controllers were designed using MATLAB *** performance of both controllers was evaluated and tested for different types of input *** simulation results showed that self-tuning fuzzy controller provides better performance,since no overshoot,small steady-state error and small settling time compared to PID controller.

关键词： Gimbal system self-tuning fuzzy proportional-integral-derivative(PID)control cross coupling

来源：评论

学校读者我要写书评

暂无评论

Conductivity Profile Reconstruction of Stroke Head Models Based on Divide-and-Conquer Method and the Genetic Algorithm

引用

IEEE Transactions on Magnetics 2024年第3期60卷 1-4页

作者： Choi, Charles T. M. Yu, Chieh-Cheng Lai, Yan-Hung National Yang Ming Chiao Tung University College of Electrical and Computer Engineering Department of Electronics and Electrical Engineering Hsinchu30010 Taiwan Institute of Electrical and Control Engineering College of Electrical and Computer Engineering National Yang Ming Chiao Tung University Hsinchu30010 Taiwan Institute of Biomedical Engineering College of Electrical and Computer Engineering National Yang Ming Chiao Tung University Hsinchu30010 Taiwan

This article used finite element (FE) analysis to study and analyze the electrical conductivity profile of simulated stroke patients based on a 45 dB signal-to-noise ratio synthesized measurement. Clinical measurement data obtained from stroke patients with electrical impedance tomography (EIT) was reported to be approximately 45 dB SNR. Weighting factors in conjunction with the divide-and-conquer method and adaptive genetic algorithm (AGA) were used. The AGA was applied with the weighting factors to identify the conductivity distribution inside the brain by minimizing the difference between the simulation and synthesized measured voltages under stroke conditions. The result shows that it might be possible to reconstruct an approximate electrical conductivity distribution based on 45 dB SNR simulated measurement of stroke data. © 2023 IEEE.

关键词： Finite element method

来源：评论

学校读者我要写书评

暂无评论

Improving Spiking Neural Network Performance Using Astrocyte Feedback for Farsi Digit Recognition

Improving Spiking Neural Network Performance Using Astrocyte...

引用

Iranian Conference on Electrical engineering (ICEE)

作者： Malihe Nazari Fariba Bahrami Mohammad Javad Yazdanpanah Human Motor Control and Computational Neuroscience Lab and Advanced Control Systems Lab School of Electrical and Computer Engineering College of Engineering University of Tehran Tehran Iran Human Motor Control and Computational Neuroscience Lab School of Electrical and Computer Engineering College of Engineering University of Tehran Tehran Iran Advanced Control Systems Lab School of Electrical and Computer Engineering College of Engineering University of Tehran Tehran Iran

The third generation of neural networks is called spiking neural networks. Spiking neural networks can not only answer all the problems that can be solved by common neural networks, they can also be computationally more powerful than them. Also, these networks are closer to the biological reality of neurons. According to these reasons, spiking neural networks have received much attention in recent years. In addition to neurons, other elements are also used in spiking neural networks, whose connection with neurons has been proven biologically. These elements are called astrocytes. In this study, we have used astrocyte local feedback in a spiking neural network to improve the accuracy of the network in a digit recognition process. To reach this goal, we use the network proposed by Diehl et al in 2015, then we added astrocyte local feedback to this network. We run the network in both states. The classification accuracy of the network in the absence of astrocytes was 88.48% on Farsi handwritten digits. After adding astrocyte local feedback, it is observed that astrocytes control the activity of neurons and modified the weight of connections based on neuron activity. In this state classification accuracy reached 90.26%. The idea was to create a neural network for learning, where, inspired by the physiological role of astrocytes at the tripartite synapse improves the performance of the neural network and we demonstrate that systems that include neurons and astrocytes perform better than systems incorporating only neurons.

关键词：

来源：评论

学校读者我要写书评

暂无评论

The Improved Decoding Algorithm of the (71, 36, 11) Quadratic Residue Code 4

The Improved Decoding Algorithm of the (71, 36, 11) Quadrati...

引用

4th IEEE International Conference on Electronics and Communication engineering, ICECE 2021

作者： Luo, Chunlan Zhu, Xiaoxia College of Computer and Control Engineering Minjiang University Fujian Fuzhou China

ISBN: (纸本)9781728194226

In the context of informatization and big data, the demands for the reliability and real-time of information transmission in wireless communication channels are increasing. Quadratic residue (QR) codes have a high prospect on error correction for reliable data conveyance over channel with noise. This paper proposes an optimized algebraic scheme for decoding (71, 36, 11) QR code for correcting up to 5 errors on one-case-by-one-case basis. This scheme is mainly to improve its algebraic decoding algorithm based on the Lin's algorithm, only in this paper, the Lin's algorithm is called LTC71 algorithm. The key technology is to use the algebraic structure of QR code and give a new discriminant condition by mathematical derivation, which can quickly detect whether there are four errors in the code. Simulation results show that the proposed decoding scheme achieves the same bit error-rate performance as LTC71 algorithm, and the decoding time is reduced by about 28.72% owing to the reduced complexity of the decoder when there are four errors in the code. ©2021 IEEE

关键词： Algebra

来源：评论

学校读者我要写书评

暂无评论

Headmotion: Human-Machine Interaction Requires Only Your Head Movement 2nd

Headmotion: Human-Machine Interaction Requires Only Your Hea...

引用

2nd EAI International Conference on Edge Computing and IoT: Systems, Management and Security, ICECI 2021

作者： Xu, Duoteng Zhu, Peizhao Zheng, Chuyu College of Mechatronics and Control Engineering Shenzhen University Guangdong Shenzhen518061 China College of Computer Science and Software Engineering Shenzhen University Guangdong Shenzhen518061 China College of Electronics and Information Engineering Shenzhen University Guangdong Shenzhen518061 China

ISBN: (纸本)9783031042300

With increasing demand for smart wearable devices and the booming development of pervasive computing, more and more new human-computer interaction methods for wearable devices are proposed to make up for the shortcomings of traditional wearable device interaction methods and improve the efficiency and ubiquity of interaction. Up to now, the human-computer interaction of wearable devices is still dominated by contact interactions, such as touching the screen and pressing physical buttons. This interaction method is convenient in most scenarios, but there are limitations in some situations, such as disabled people cannot use their hands for human-computer interaction, and drivers are not suitable for touch interaction with their hands when driving. To address this shortcoming, we designed a natural interaction system for ear-worn smart devices, which includes a deep network recognition model based on acceleration, angular velocity and angle data of head motion collected by inertial units worn on the ear. The interaction system now can realize human-computer interaction of head motion in various complex scenarios, which greatly liberates the user’s hands. We have experimentally verified the excellent accuracy and real-time performance of our designed system. © 2022, ICST Institute for computer Sciences, Social Informatics and Telecommunications engineering.

关键词： Human computer interaction

来源：评论

学校读者我要写书评

暂无评论

Research on Intelligent Scene Generation Based on Unity3D 16th

Research on Intelligent Scene Generation Based on Unity3D

引用

16th International Conference on Intelligent Information Hiding and Multimedia Signal Processing, IIH-MSP 2020 in conjunction with the 13th International Conference on Frontiers of Information Technology, Applications and Tools, FITAT 2020

作者： Zheng, Lingbin Li, Menghua Gao, Yuxi Chen, Hang Zhang, Fuquan College of Computer and Control Engineering Minjiang University Fuzhou350108 China

ISBN: (纸本)9789813364196

This paper presents a systematic intelligent scene generation algorithm, based on which the user randomly generates the required scene map. Using this algorithm, we can pick out the material needed by the user from the 3D model and put the material into scene generation module to facilitate the implementation of the subsequent scene display module. At the same time, we use the random. Range to generate the material coordinates of the specified range and store it in the array. Here, we will elaborate the material object generation, judgment object rationality, object instantiation, and other algorithms. The basic operation process of scene generation system is divided into four steps: First, users can choose their own needs through UI interface. Second, the system calls relevant algorithms to analyze user requirements and calls the required materials. Next, when the system gets the specified materials, the system can combine these materials freely according to certain rules to generate scenes. Finally, the generated scene is displayed to the user by switching the interface shot. © 2021, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： 3D modeling

来源：评论

学校读者我要写书评

暂无评论

Street Lamp Status Warning System Based on Internet of Things Technology

引用

Journal of Electronic Research and Application 2024年第4期8卷 154-160页

作者： Hanli Wang Yuanzhi Liu Yilin Wu College of Computer and Control Engineering Northeast Forestry UniversityHarbin 150040China College of Civil Engineering and Transportation Northeast Forestry UniversityHarbin 150040China College of Wildlife and Nature Reserves Northeast Forestry UniversityHarbin 150040China

This paper proposes a street light warning system based on Internet of Things(IoT)technology,which uses cameras to detect moving targets such as vehicles and pedestrians around the system and adjust the brightness of street lights according to road conditions to reduce unnecessary power *** system has a mature self-fault detection mechanism and is equipped with a wireless communication device for data exchange and timely communication with the host computer *** intelligent street lamp system in this paper can be used to reduce the occurrence of pedestrian and vehicle accidents at intersections,and at the same time reduce the consumption of manpower and material resources for street lamp troubleshooting,to achieve energy conservation and emission reduction.

关键词： Internet of Things Early warning system Intelligent transportation

来源：评论

学校读者我要写书评

暂无评论

Traditional Chinese Medicine Health Status Identification with Graph Attention Network 1

引用

4th International Conference on Machine Learning for Cyber Security, ML4CS 2022

作者： Fu, Amin Ma, Jishun Wang, Chuansheng Zhou, Changen Li, Zuoyong Teng, Shenghua College of Electronic and Information Engineering Shandong University of Science and Technology Qingdao266590 China Department of Automatic Control Technical Polytechnic University of Catalonia Barcelona08034 Spain Research Base of Traditional Chinese Medicine Syndrome Fujian University of Traditional Chinese Medicine Fuzhou350122 China Fujian Provincial Key Laboratory of Information Processing and Intelligent Control College of Computer and Control Engineering Minjiang University Fuzhou350121 China

ISBN: (数字)9783031200960

ISBN: (纸本)9783031200953

The Traditional Chinese Medicine Health Status Identification plays an important role in TCM diagnosis and prescription recommendation. In this paper, we propose a method of Status Identification via Graph Attention Network, named SIGAT, which captures the complex medical correlation in the symptom-syndrome graph. More specifically, we construct a symptom-syndrome graph in that symptoms are taken as nodes and the edges are connected by syndromes. And we realize automatic induction of symptom to state element classification by using the attention mechanism and perceptron classifier. Finally, we conduct experiments by using hamming loss, coverage, 0/1 error, ranking loss, average precision, macro-F1 score, and micro-F1 score as evaluation metrics. The results demonstrate that the SIGAT model outperforms comparison algorithms on Traditional Chinese Medicine Prescription Dictionary dataset. The case study results suggest that the proposed method is a valuable way to identify the state element. The application of the graph attention network classification algorithm in TCM health status identification is of high precision and methodological feasibility. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Classification (of information)

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：