检索结果-内蒙古大学图书馆

SAMFNet: Scene-aware sampling and multi-stage fusion for multimodal 3D object detection

Alexandria engineering Journal 2025年 126卷 90-104页

作者： Wang, Baotong Xia, Chenxing Gao, Xiuju Ge, Bin Li, Kuan-Ching Fang, Xianjin Zhang, Yan Yang, Yuan College of Computer Science and Engineering Anhui University of Science and Technology Huainan232001 China College of Electrical and Information Engineering Anhui University of Science and Technology Huainan232001 China Department of Computer Science and Information Engineering Providence University Taichung43301 China The School of Electronics and Information Engineering Anhui University Hefei230039 China School of Mathematics and Big Data Anhui University of Science and Technology Huainan232001 China

Recently, multimodal 3D object detection (M3OD) that fuses the complementary information from LiDAR data and RGB images has gained significant attention. However, the inherent structural differences between point clouds and images pose fusion challenges, significantly hindering the exploration of correlations within multimodal data. To address this issue, this paper introduces an enhanced multimodal 3D object detection framework (SAMFNet), which leverages virtual point clouds generated from depth completion. Specifically, we design a scene-aware sampling module (SASM) that employs tailored sampling strategies for different bins based on the density distribution of point clouds. This effectively alleviates the detection bias problem while ensuring the key information of virtual points, significantly reducing the computational cost. In addition, we introduce a multi-stage feature fusion module (MSFFM) that embeds point-level and regional-adaptive feature fusion strategies to generate more informative multimodal features by fusing features with different granularities. To further improve the accuracy of model detection, we also introduce a confidence prediction branch unit (CPBU), which improves the detection accuracy by predicting the confidence of feature classification in the intermediate stage. Extensive experiments on the challenging KITTI dataset demonstrate the validity of our model. © 2025 The Authors

关键词： Image fusion

来源：评论

学校读者我要写书评

暂无评论

Scheduling Bi-Objective Lot-Streaming Hybrid Flow Shops with Consistent Sublots via an Enhanced Artificial Bee Colony Algorithm

引用

Complex System Modeling and Simulation 2025年第1期5卷 46-67页

作者： Lu, Benxue Gao, Kaizhou Duan, Peiyong Slowik, Adam School of Computer Science Liaocheng University Liaocheng252000 China Macau Institute of Systems Engineering Macau University of Science and Technology Macau999078 China School of Information and Automation Engineering Qilu University of Technology Jinan250353 China Koszalin University of Technology Department of Electronics and Computer Science Koszalin75-453 Poland

This work addresses bi-objective hybrid flow shop scheduling problems considering consistent sublots (Bi-HFSP_CS). The objectives are to minimize the makespan and total energy consumption. First, the Bi-HFSP_CS is formalized, followed by the establishment of a mathematical model. Second, enhanced version of the artificial bee colony (ABC) algorithms is proposed for tackling the Bi-HFSP_CS. Then, fourteen local search operators are employed to search for better solutions. Two different O-learning tactics are developed to embed into the ABC algorithm to guide the selection of operators throughout the iteration process. Finally, the proposed tactics are assessed for their efficacy through a comparison of the ABC algorithm, its three variants, and three effective algorithms in resolving 95 instances of 35 different problems. The experimental results and analysis showcase that the enhanced ABC algorithm combined with O-learning (QABC1) demonstrates as the top performer for solving concerned problems. This study introduces a novel approach to solve the Bi-HFSP_CS and illustrates its efficacy and superior competitive strength, offering beneficial perspectives for exploration and research in relevant domains. © 2021 TUP.

关键词： Energy utilization

来源：评论

学校读者我要写书评

暂无评论

Comparative Analysis of Machine Learning Algorithm;for Conversion Predictors of Clinically Isolated Syndrome (CIS) to Multiple Sclerosis (MS) 4

Comparative Analysis of Machine Learning Algorithm;for Conve...

引用

4th International Conference on Sentiment Analysis and Deep Learning, ICSADL 2025

作者： Mendanha, Serena Gudibandi, Keerthi Reddy Hajarathaiah, Koduru Gudibandi, Bharat Reddy Enduri, Murali Krishna School of Computer Science and Engineering VIT-AP University Amaravati India School of Electronics Engineering VIT-AP University Amaravati India Srm University Department of Computer Science and Engineering AP India

ISBN: (纸本)9798331523923

The central nervous system is impacted by multiple sclerosis (MS), a chronic neurological condition that causes significant cognitive and physical deficits. Better disease management and prompt intervention depend on early and precise detection. Effective diagnosis of MS is hampered by a number of factors, such as small datasets, significant clinical presentation variability, difficult feature selection, model generalization problems, and integration of multimodal data such as magnetic resonance imaging and genetic markers. Several machine learning (ML) models are assessed in this study in order to predict the development of clinically isolated syndrome (CIS) to multiple sclerosis. Using clinical and magnetic resonance data from patients with CIS at risk of developing MS, we evaluate the effectiveness of support vector machines (SVM), K nearest neighbor (KNN), decision trees (DT), random forests (RF), logistic regression (LR), Gaussian naive Bayes (Gaussian NB) and XGBoost (XG). Evaluation is performed using performance criteria including F1 score, recall, precision, and precision. According to our research, Random Forest has the best prediction accuracy, which makes it a potentially useful tool for helping doctors diagnose and treat MS patients early. Notwithstanding these developments, issues like model interpretability and data scarcity still exist. In order to improve diagnosis precision, future research will concentrate on enhancing these models by integrating deep learning methods, genetic markers,, and more advanced imaging modalities. © 2025 IEEE.

关键词： Magnetic resonance imaging

来源：评论

学校读者我要写书评

暂无评论

Energy Efficient Dual User Association for Large Scale IRS-Aided mmWave Communication Networks

引用

China Communications 2025年第1期22卷 182-195页

作者： Chen Guolin Deng Yiqin Huang Xiaoxia Fang Yuguang School of Electronics and Communication Engineering Sun Yat-sen UniversityShenzhen 518107China School of Control Science and Engineering Shandong UniversityJinan 250100China Department of Computer Science City University of Hong KongHong Kong 999077China

The deployment of multiple intelligent reflecting surfaces(IRSs)in blockage-prone millimeter wave(mmWave)communication networks have garnered considerable attention *** the remarkably low circuit power consumption per IRS element,the aggregate energy consumption becomes substantial if all elements of an IRS are turned on given a considerable number of IRSs,resulting in lower overall energy efficiency(EE).To tackle this challenge,we propose a flexible and efficient approach that individually controls the status of each IRS ***,the network EE is maximized by jointly optimizing the associations of base stations(BSs)and user equipments(UEs),transmit beamforming,phase shifts of IRS elements,and the associations of individual IRS elements and *** problem is efficiently addressed in two ***,the Gale-Shapley algorithm is applied for BS-UE association,followed by a block coordinate descent-based algorithm that iteratively solves the subproblems related to active beamforming,phase shifts,and element-UE *** reduce the tremendous dimensionality of optimization variables introduced by element-UE associations in large-scale IRS networks,we introduce an efficient algorithm to solve the associations between IRS elements and *** results show that the proposed elementwise control scheme improves EE by 34.24% compared to the network with IRS-all-on scheme.

关键词： energy efficiency intelligent reflecting surface,millimeter-wave communication

来源：评论

学校读者我要写书评

暂无评论

ViF-SD2E: a robust weakly-supervised framework for neural decoding

引用

Neural Computing and Applications 2025年第9期37卷 6645-6661页

作者： Feng, Jingyi Luo, Yong Song, Shuang Hu, Han National Engineering Research Center for Multimedia Software School of Computer Science Wuhan University Wuhan430072 China School of Information and Electronics Beijing Institute of Technology Beijing100081 China

Neural decoding plays a vital role in the interaction between the brain and the outside world. Our task in this paper is to decode the movement track of a finger directly based on the neural data. Existing neural decoding solutions primarily perform some preprocessing operations on neural data before feeding them into existing models (such as LSTM) for decoding. However, these solutions either are prone to overfitting or cannot well exploit the spatial and temporal information. In our previous observations, there is a symmetrical phenomenon between the unsupervised decoded trajectory and the ground truth trajectory within the activity space. This precisely motivates us to propose (or derive) a robust weakly-supervised framework (or model structure), called ViF-SD2E, for neural decoding. In particular, it consists of a space-division (SD) module and an exploration–exploitation (2E) strategy, to effectively exploit both the spatial information of the outside world and the temporal information of neural activity, where the SD2E output is analogized with the weak 0/1 vision feedback (ViF) label for training. Extensive experiments demonstrate the effectiveness of our method, which can sometimes be comparable to supervised counterparts. Therefore, we redirect our attention to the information (hidden in data) ViF-SD2E conveys to us. In other words, we believe that the advantage of ViF-SD2E lies in the fact that its processing steps are objectively determined by the inherent attributes (i.e., symmetry) of the neural data, or rather, the model structure is fixed. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2025.

关键词： Space division multiple access

来源：评论

学校读者我要写书评

暂无评论

Real-Time Differential Ultrasonic Flow Sensing Enabled by PMUT Phased Array with a Novel V-Shaped Beam Pattern 38

Real-Time Differential Ultrasonic Flow Sensing Enabled by PM...

引用

38th IEEE International Conference on Micro Electro Mechanical Systems, MEMS 2025

作者： Gao, Yufeng Wang, Xili Zhao, Lei Lu, Yipeng Peking University School of Integrated Circuits China Peking University School of Electronics Engineering and Computer Science China

ISBN: (纸本)9798331508890

Ultrasonic flow sensing offers significant advantages for non-invasive, adaptive monitoring in various scenarios. Traditional ultrasonic flowmeters are composed of paired transducers, which are used as TX/RX alternately to obtain the upstream and downstream flow information sequentially. Here, we demonstrated real-time ultrasonic gas flow sensing with a novel V-shaped beam pattern generated by a compact 3.6mm×3.6mm piezoelectric micromachined ultrasonic transducer (PMUT) phased array based on PZT thin film. By utilizing the grating lobe produced through optimized array pitch and sequential control, this 5-channel PMUT array breaks the conventional design limitations typically associated with grating lobes. The array generates a symmetric V-shaped beam pattern with dual main lobes measured at 27° and 153°, enabling real-time differential flow sensing in a single measurement (1000 times measurements in 1 second), and excellent linearity and robustness of measurement results under 1L/min-5L/min airflow. © 2025 IEEE.

关键词： Ultrasonic flowmeters

来源：评论

学校读者我要写书评

暂无评论

SmokerBeacon: Hybrid Real-Time Smoking Detection Using Object Detection and Gas Sensor

SmokerBeacon: Hybrid Real-Time Smoking Detection Using Objec...

引用

2025 IEEE International Students' Conference on Electrical, electronics and computer science, SCEECS 2025

作者： Harshavardhan, S. Upender, Patri Ganesh, N. Giftsy, Sharon Vellore Institute of Technology School of Computer Science and Engineering Chennai India Vellore Institute of Technology School of Electronics Engineering Chennai India

ISBN: (纸本)9798331529833

Enforcing smoking bans in public areas remains a challenge due to limitations in conventional monitoring methods. This paper introduces SmokerBeacon, an innovative system for real-time detection of smoking activities in restricted zones. SmokerBeacon uses gas sensors and advanced image classification - YOLO to identify smoking activities. The system catego-rizes detection scenarios into three types: (i) instances where smoking actions are detected by YOLO without corresponding signals from gas sensors, (ii) cases where YOLO fails to detect smoking actions despite gas sensors detecting smoking-related substances, and (iii) situations where both smoking activities and corroborating signals from gas sensors confirm smoking. Each scenario triggers specific actions to improve enforcement and foster healthier environments. By generating timely alerts and enabling proactive intervention, SmokerBeacon mitigates risks associated with smoking in prohibited areas, leveraging IoT technology. © 2025 IEEE.

关键词： Chemical sensors

来源：评论

学校读者我要写书评

暂无评论

Soft Growing Robot Explore Unknown Environments Through Obstacle Interaction

引用

IEEE Robotics and Automation Letters 2025年第6期10卷 6015-6022页

作者： Wu, Haoran Sun, Fuchun Huang, Canwei Huang, Haiming Chu, Zhongyi Beihang University School of Instrument and Optoelectronics Engineering Beijing China Tsinghua University Department of Computer Science and Technology Beijing China Shenzhen University College of Electronics and Information Engineering Shenzhen China

In low-light, unstructured, and confined environments, performing Simultaneous Localization and Mapping (SLAM) with conventional methods presents significant challenges. Soft growing robots, characterized by their compliance and extensibility, interact safely with the environment, making them well-suited for navigation in such environments. Through collision-based guidance, the robot can gather environmental data via morphological adaptations. Based on this, we developed the sensing capabilities of the soft growing robot, retaining its flexibility while enabling effective environmental interaction and perception. The robot employs a gyroscope combined with an encoder to track the end-effector trajectory and uses flexible proximity sensing to detect obstacles. By fusing the information from these sensors, we propose a multi-sensor fusion strategy for environmental exploration of the soft growing robot. The robot navigates unknown environments by employing pre-bending based on prior environmental data and utilizing pneumatic artificial muscles. In multi-obstacle environmental exploration, the path prediction error is less than 3.5% of the robot's total length, enabling greater environmental coverage with fewer exploration attempts © 2016 IEEE.

关键词： End effectors

来源：评论

学校读者我要写书评

暂无评论

DIEONet:Domain-Invariant Information Extraction and Optimization Network for Visual Place Recognition

引用

computers, Materials & Continua 2025年第3期82卷 5019-5033页

作者： Shaoqi Hou Zebang Qin Chenyu Wu Guangqiang Yin Xinzhong Wang Zhiguo Wang School of Computer Science and Technology Xinjiang UniversityUrumqi830046China School of Information and Software Engineering University of Electronic Science and Technology ofChinaChengdu611731China Institute of Public Security Kash Institute of Electronics and Information IndustryKashi844000China

Visual Place Recognition(VPR)technology aims to use visual information to judge the location of agents,which plays an irreplaceable role in tasks such as loop closure detection and *** is well known that previous VPR algorithms emphasize the extraction and integration of general image features,while ignoring the mining of salient features that play a key role in the discrimination of VPR *** this end,this paper proposes a Domain-invariant Information Extraction and Optimization Network(DIEONet)for *** core of the algorithm is a newly designed Domain-invariant Information Mining Module(DIMM)and a Multi-sample Joint Triplet Loss(MJT Loss).Specifically,DIMM incorporates the interdependence between different spatial regions of the feature map in the cascaded convolutional unit group,which enhances the model’s attention to the domain-invariant static object *** Loss introduces the“joint processing of multiple samples”mechanism into the original triplet loss,and adds a new distance constraint term for“positive and negative”samples,so that the model can avoid falling into local optimum during *** demonstrate the effectiveness of our algorithm by conducting extensive experiments on several authoritative *** particular,the proposed method achieves the best performance on the TokyoTM dataset with a Recall@1 metric of 92.89%.

关键词： Visual place recognition domain-invariant information mining module multi-sample joint triplet loss

来源：评论

学校读者我要写书评

暂无评论

OLMS: A Flexible Online Learning Multi-Path Scheduling Framework

引用

IEEE Transactions on Network science and engineering 2025年第3期12卷 2277-2291页

作者： Cai, Kechao Chen, Zhuoyue Zhang, Jinbei Lui, John C. S. Shenzhen Campus of Sun Yat-sen University School of Electronics and Communication Engineering Shenzhen510275 China The Chinese University of Hong Kong Department of Computer Science and Engineering Shatin Hong Kong

Over the past decade, there has been a tremendous surge in the inter-connectivity among hosts in networks. Many multi-path transport protocols, such as MPTCP, MPQUIC, and MPRDMA, have emerged to facilitate multi-path data transmissions between pairs of hosts. However, existing packet schedulers in these protocols are quite limited as they neglect the stochastic nature inherent in heterogeneous paths, such as, round-trip time and available bandwidth. Moreover, users have diverse requirements;for instance, some prioritize low latency, while others consistently seek to achieve high bandwidth. In this paper, we propose a flexible Online Learning Multi-path Scheduling (OLMS) framework to schedule packets to multiple paths and meet various user-defined requirements by learning the dynamic characteristics of paths in various applications. Specifically, we consider two types of applications, which are 1) maxRTT constrained and 2) bandwidth constrained, and use OLMS to schedule packets to satisfy the distinct user-defined requirements. Our theoretical analysis demonstrates that OLMS achieves guarantees with sublinear regret and sublinear violation. Furthermore, we implement a prototype of OLMS in MPQUIC and conduct experiments across different scenarios. Our experiments on Mininet show that OLMS enables an 8.42%–18.71% increase in bandwidth utilization in the maxRTT constrained application and negligible violations of user-defined requirements in both applications compared to other schedulers. Additionally, OLMS reduces flow completion times by 4.22%–10.26% compared to other schedulers, all without incurring large overhead. © 2013 IEEE.

关键词： Bandwidth

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：