检索结果-内蒙古大学图书馆

2024 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2024

作者： Ali, Md. Mamun Ahmed, Kawsar Bui, Francis M. Wu, Fang-Xiang University of Saskatchewan Division of Biomedical Engineering Saskatoon Canada University of Saskatchewan Department of Electrical and Computer Engineering Saskatoon Canada University of Saskatchewan Division of Biomedical Engineering Department of Mechanical Engineering Department of Computer Science Saskatoon Canada

ISBN: (纸本)9798350386226

Druggable proteins are defined as proteins that can interact with drugs to modulate certain biological activity. The identification of druggable proteins holds significant clinical importance, directly impacting the development of targeted therapies for diseases like cancer and metabolic disorders. Identifying druggable proteins involves various methods, including computational prediction models, mass spectrometry (MS), and biochemical assays, but achieving high accuracy remains a challenge. This study proposes DrugEL, an ensemble learning model that uses Bayesian inference to integrate predictions from multiple algorithms: Random Forest (RF), K-Nearest Neighbor (KNN), LightGBM (LGBM), and Decision Tree (DT) with seven feature extraction methods (LSA, AAC, PAAC, GAAC, NMBroto, AAIndex, and KNN). The results show that DrugEL outperforms existing models in terms of accuracy (0.9758), MCC (0.9515), AUC (0.9758), sensitivity (0.9742) and specificity (0.9774), particularly excelling with the LSA method. © 2024 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

An Efficient Approach for Appliances Energy Prediction using Differential Evolution Optimization and Light GBM Machine Learning Model

An Efficient Approach for Appliances Energy Prediction using...

引用

2024 International Conference on Sustainable Energy: Energy Transition and Net-Zero Climate Future, ICUE 2024

作者： Vakharia, Vinay Dave, Vipul Borade, Himanshu Agrawal, Hitesh Padia, Nandan Pandit Deendayal Energy University Department of Mechanical Engineering Gandhinagar India Parul Institute of Engineering and Technology Department of Mechanical Engineering Vadodara India Medi-Caps University Mechanical Engineering Department Indore India Pandit Deendayal Energy University Department of Computer Science Engineering Gandhinagar India

ISBN: (纸本)9798331517076

This study presents a new method for assessing the energy use of appliances in a low energy residence with the goal of improving energy consumption predictions. Information was collected at 10-minute intervals throughout a period of 137 days. The collected data includes a wide range of equipment, with a specific emphasis on lighting and the relationship between humidity levels and room occupancy. The dataset was divided into three subgroups depending on the lighting feature in order to assess the predictive importance of various parameters: all records, recordings without lighting, and records only including lighting. The suggested investigation employs a hybrid machine learning framework that integrates Extreme Gradient Boosting (XGBoost) and Light Gradient Boosting Machine (Light GBM) to forecast energy consumption. In order to improve the precision of the model, a sophisticated differential evolution approach is used to optimize the model's parameters. The models were compared using several performance indicators, such as the mean absolute error (MAE), root mean square error (RMSE), coefficient of determination (R2), and mean absolute percentage error (MAPE). The prediction results showed low error rates and strong correlation coefficients for all of these measurements, highlighting the usefulness of our technique in improving operational efficiency and forecast accuracy in energy management. The combination of bio-inspired optimization algorithms with ensemble machine learning approaches has significant promise for improving energy consumption predictions, which are essential for sustainable home energy management. © 2024 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

A Normalizing Flow-Based Bidirectional Mapping Residual Network for Unsupervised Defect Detection

引用

computers, Materials & Continua 2024年第2期78卷 1631-1648页

作者： Lanyao Zhang Shichao Kan Yigang Cen Xiaoling Chen Linna Zhang Yansen Huang School of Mechanical Engineering Guizhou UniversityGuiyang550025China School of Computer Science and Engineering Central South UniversityChangsha410083China School of Computer and Information Technology Beijing Jiaotong UniversityBeijing100044China College of Civil Engineering Guizhou UniversityGuiyang550025China Guizhou Lianjian Civil Engineering Quality Inspection Monitoring Center Co. Ltd.Guiyang550025China

Unsupervised methods based on density representation have shown their abilities in anomaly detection,but detection performance still needs to be ***,approaches using normalizing flows can accurately evaluate sample distributions,mapping normal features to the normal distribution and anomalous features outside ***,this paper proposes a Normalizing Flow-based Bidirectional Mapping Residual Network(NF-BMR).It utilizes pre-trained Convolutional Neural Networks(CNN)and normalizing flows to construct discriminative source and target domain feature ***,to better learn feature information in both domain spaces,we propose the Bidirectional Mapping Residual Network(BMR),which maps sample features to these two spaces for anomaly *** two detection spaces effectively complement each other’s deficiencies and provide a comprehensive feature evaluation from two perspectives,which leads to the improvement of detection *** experimental results on the MVTec AD and DAGM datasets against the Bidirectional Pre-trained Feature Mapping Network(B-PFM)and other state-of-the-art methods demonstrate that the proposed approach achieves superior *** the MVTec AD dataset,NF-BMR achieves an average AUROC of 98.7%for all 15 ***,it achieves 100%optimal detection performance in five *** the DAGM dataset,the average AUROC across ten categories is 98.7%,which is very close to supervised methods.

关键词： Anomaly detection normalizing flow source domain feature space target domain feature space bidirectional mapping residual network

来源：评论

学校读者我要写书评

暂无评论

Securing IoT Systems with AI-Infused Software and Virtual Replica Models 2

Securing IoT Systems with AI-Infused Software and Virtual Re...

引用

2nd IEEE International Conference on Integrated Intelligence and Communication Systems, ICIICS 2024

作者： Supriya, K. Sangeetha Jeno Lovesum, S.P. Arora, Renuka Bhatia, Rishu Yadwad, Sunita Natrayan, L. Department of Computer Science & Engineering Christ University Bengaluru India Department of Computer Science & Engineering Jagannath University NCR Bahadurgarh India Department of Electronics and Communication Engineering Ganga Institute of Technology and Management Jhajjar India Department of Computer Science and Engineering Faculty of Engineering and Technology Parul institute of Engineering and Technology Parul University Vadodara India Department of Mechanical Engineering Saveetha School of Engineering SIMATS Chennai India

ISBN: (纸本)9798331504960

The proliferation of Internet of Things (IoT) devices has introduced significant security challenges due to the increased attack surface and the inherent vulnerabilities of interconnected systems. This paper proposes a novel security framework that integrates Artificial Intelligence (AI)-infused software and Virtual Replica Models, or Digital Twins, to enhance the robustness of IoT systems. The framework leverages AI-driven anomaly detection and predictive analysis to identify potential threats in real-time, while Digital Twins provide a virtual replica of the IoT ecosystem for continuous monitoring and simulation-based threat assessment. By fusing these technologies, the proposed solution enables proactive security measures, ensuring rapid response to cyberattacks and continuous system optimization. Extensive simulations and experimental results demonstrate the system’s ability to reduce attack detection times by 30%, while improving overall system resilience and minimizing false positive rates. This approach provides a scalable and adaptable solution for securing IoT infrastructures in various industries. © 2024 IEEE.

关键词： Risk assessment

来源：评论

学校读者我要写书评

暂无评论

Learning Bipedal Walking on a Quadruped Robot via Adversarial Motion Priors 25th

Learning Bipedal Walking on a Quadruped Robot via Adversa...

引用

25th Annual Conference on Towards Autonomous Robotic Systems, TAROS 2024

作者： Peng, Tianhu Bao, Lingfan Humphreys, Joseph Delfaki, Andromachi Maria Kanoulas, Dimitrios Zhou, Chengxu School of Mechanical Engineering University of Leeds Leeds United Kingdom Department of Computer Science University College London London United Kingdom

ISBN: (纸本)9783031720611

Previous studies have successfully demonstrated agile and robust locomotion in challenging terrains for quadrupedal robots. However, the bipedal locomotion mode for quadruped robots remains unverified. This paper explores the adaptation of a learning framework originally designed for quadrupedal robots to operate blind locomotion in biped mode. We leverage a framework that incorporates Adversarial Motion Priors with a teacher-student policy to enable imitation of a reference trajectory and navigation on tough terrain. Our work involves transferring and evaluating a similar learning framework on a quadruped robot in biped mode, aiming to achieve stable walking on both flat and complicated terrains. Our simulation results demonstrate that the trained policy enables the quadruped robot to navigate both flat and challenging terrains, including stairs and uneven surfaces. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Advancing Robotic Jumping with CVT Enhanced SEA 25th

Advancing Robotic Jumping with CVT Enhanced SEA

引用

25th Annual Conference on Towards Autonomous Robotic Systems, TAROS 2024

作者： Sun, Jingcheng Zhou, Chengxu School of Mechanical Engineering University of Leeds Leeds United Kingdom Department of Computer Science University College London London United Kingdom

ISBN: (纸本)9783031720611

Series-elastic actuation (SEA) is widely employed on hopping robots due to its capability to diminish energy consumption and peak torque requirements. However, scant attention has been given in existing studies to the jump height achieved by robots utilizing SEA. To maximise jump height while retaining SEA’s benefits, a solution to improve the actuator involves having a variable mechanical advantage (MA) gearbox between the elastic element and the end-effector. Continuously variable transmission (CVT) can produce such a precise MA profile with relatively straightforward structures. Although previous studies have incorporated CVT in robotics, with a predominant focus on wheeled robots, the potential advantages of using CVT on jumping robots have been overlooked. In this study, mathematical modelling is utilized to simulate and analyse the advantages of having a CVT-enhanced SEA (C-SEA) in terms of achieving higher jumps and protecting structural integrity for hopping robots. The results indicate that the C-SEA manages to reduce the peak ground reaction force by approximately 50% compared to the regular SEA. Moreover, C-SEA demonstrates superior performance in most cases with higher motor rotor mass and viscous damping coefficient when actuated by a motor with linear behaviour. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： End effectors

来源：评论

学校读者我要写书评

暂无评论

A Feature Reduction Approach Based on Adaptively Weighted Neighborhood Rough Sets 6

A Feature Reduction Approach Based on Adaptively Weighted Ne...

引用

6th International Conference on Frontier Technologies of Information and computer, ICFTIC 2024

作者： Peng, Gongjian Ge, Hao Yang, Chuanjian Yan, Yuanting Anhui University School of Computer Science and Technology Hefei China Chuzhou University School of Computer Science and Technology Chuzhou China Chuzhou University School of Mechanical and Electrical Engineering Chuzhou China

ISBN: (纸本)9798331541750

Feature reduction based on weighted neighborhood rough sets has been widely applied in machine learning and data mining. In existing weighted neighborhood rough set models, the weight of each feature is calculated independently and fixed without adjusting according to the selected feature set. Therefore, it cannot guarantee that the most significant feature for the selected feature set can always be selected. For this issue, we introduce adaptive weights into neighborhood relations, then propose a novel feature reduction approach. First, the separability of individual features and feature subsets is analyzed to adaptively calculate the weights of features based on the current selected feature set. Then, adaptively weighted neighborhood relations are defined to construct an adaptively weighted neighborhood rough set (AWNRS) model. Furthermore, a greedy search algorithm (DAWNRS) based on AWNRS is proposed to select a feature subset that has both high dependency and strong correlation. Finally, the proposed algorithm is compared with other representative reduction algorithms by using eight UCI datasets on three classifiers. Experimental results show that the proposed approach achieves superior classification performance. © 2024 IEEE.

关键词： Feature Selection

来源：评论

学校读者我要写书评

暂无评论

Expansive detector via hybrid temporal and transposed convolutional mechanism for weld proximity defects

引用

Soft Computing 2025年第6期29卷 3021-3034页

作者： Chen, Zihua Zhang, Runmei Chen, Zhong Yuan, Bin Zheng, Yu Li, Kuan-Ching School of Mechanical and Electrical Engineering Anhui Jianzhu University Hefei230000 China Department of Computer Science and Information Engr Providence University Taichung43301 Taiwan

Detection of weld proximity defects aims to recognize and classify different proximity defects in industrial welding. It presents some characteristics such as the small-target, localized diffusion, and dense distribution, which is difficult in steel-sheet welding engineering. Due to small-target size, localized diffusion, the similar and dense distribution, and imbalanced sample numbers, the existing detection models with the fixed receptive field are weak in detecting weld proximity defects. To solve the problem, we propose an expansive you-only-look-once detection model, called DRB-YOLOv5. It integrates a novel dilation causal convolution cross-stage partial network and the improved Focal Loss function. First, we provide a dilation causal transposed-convolution residual block cross-stage partial network to amplify and extract features of weld proximity defects effectively. Further, we reduce the block number of two middle Resblock Bodies in the Backbone of DRB-YOLOv5 to avoid network overfitting. Second, we design a Prediction Head via the Bias Focal Loss to balance positive and negative samples and improve the detection accuracy of various number-imbalanced weld defects. Finally, we compare the proposed model with some related existing models via the real weld proximity defects dataset. Experimental results show that the proposed DRB-YOLOv5 can present superior effects, mainly including mAP: 89.21%, F1: 83.50%, and recall: 80.73%. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2025.

关键词： Bias focal loss Improved cross-stage partial network Object detection Weld proximity defects

来源：评论

学校读者我要写书评

暂无评论

A Fault-Tolerant Mobility-Aware Caching Method in Edge Computing

引用

computer Modeling in engineering & sciences 2024年第7期140卷 907-927页

作者： Yong Ma Han Zhao Kunyin Guo Yunni Xia Xu Wang Xianhua Niu Dongge Zhu Yumin Dong School of Computer Information Engineering Jiangxi Normal UniversityNanchang330000China School of Digital Industry Jiangxi Normal UniversityShangrao334000China The College of Computer Science Chongqing UniversityChongqing400044China College of Mechanical and Vehicle Engineering Chongqing UniversityChongqing400030China School of Computer and Software Engineering Xihua UniversityChengdu610039China Electric Power Research Institute of State Grid Ningxia Electric Power Company Ltd. Yinchuan750002China College of Computer and Information Science Chongqing Normal UniversityChongqing401331China

Mobile Edge Computing(MEC)is a technology designed for the on-demand provisioning of computing and storage services,strategically positioned close to *** the MEC environment,frequently accessed content can be deployed and cached on edge servers to optimize the efficiency of content delivery,ultimately enhancing the quality of the user ***,due to the typical placement of edge devices and nodes at the network’s periphery,these components may face various potential fault tolerance challenges,including network instability,device failures,and resource *** the dynamic nature ofMEC,making high-quality content caching decisions for real-time mobile applications,especially those sensitive to latency,by effectively utilizing mobility information,continues to be a significant *** response to this challenge,this paper introduces FT-MAACC,a mobility-aware caching solution grounded in multi-agent deep reinforcement learning and equipped with fault tolerance *** approach comprehensively integrates content adaptivity algorithms to evaluate the priority of highly user-adaptive cached ***,it relies on collaborative caching strategies based onmulti-agent deep reinforcement learningmodels and establishes a fault-tolerancemodel to ensure the system’s reliability,availability,and *** results unequivocally demonstrate that FTMAACC outperforms its peer methods in cache hit rates and transmission latency.

关键词： Mobile edge networks mobility fault tolerance cooperative caching multi-agent deep reinforcement learning content prediction

来源：评论

学校读者我要写书评

暂无评论

Experimental Investigation and Weibull Statistical Analysis on Tensile Behaviour of Carbon/Epoxy Composites

引用

Journal of The Institution of Engineers (India): Series D 2024年第3期105卷 1373-1383页

作者： Amar, Thakur Abhinav Kumar, Amit Yadav, D.K. Department of Production and Industrial Engineering Birla Institute of Technology Ranchi JH Mesra835215 India Department of Mechanical Engineering National Institute of Technology BH Patna800005 India Department of Computer Science and Engineering National Institute of Technology JH Jamshedpur831014 India

This paper is concerned with the experimental and theoretical evaluation of the tensile strength of carbon fabric-reinforced epoxy composites developed using hand lay-up and vacuum bagging techniques. The developed CFRP composite laminates were subjected to tensile tests as per ASTM D3039 at different strain rates of 1 s−1, 10 s−1, and 100 s−1. The statistical analysis of the experimental results was conducted using a two-parameter Weibull distribution function. The results showed an increase in tensile strength with an increase in strain rate for composite laminates produced using both fabrication techniques. The tensile modulus also showed an increasing trend with respect to strain rate, but the increase was marginal, while elongation at break showed a decreasing trend. For all cases of strain rate, the vacuum bag-fabricated composite laminates showed higher tensile strength and modulus values except for elongation at break when compared with the laminates fabricated with hand lay-up. Cumulative probability density data, along with Weibull parameters, were utilised to determine theoretical tensile strength. The projected tensile strength values closely matched the experimental results, with a minimal difference of approximately 6.2% observed in the context of composite laminates fabricated under vacuum bag conditions. Fracture analysis identified distinct failure mechanisms: adhesive failure at the fabric/matrix interface for the hand lay-up method and brittle fracture as the predominant failure mode for laminates produced using vacuum bagging techniques. © The Institution of Engineers (India) 2023.

关键词： Tensile strength

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：