检索结果-内蒙古大学图书馆

2025 International Conference on Control, Automation, and Instrumentation, IC2AI 2025

作者： Chaaban, Omar Daher, Leen Ghaddar, Yara Zantout, Nader Asmar, Daniel Daher, Naseem American University of Beirut Department of Mechanical Lebanon American University of Beirut Electrical and Computer Engineering Lebanon

ISBN: (纸本)9798331529604

Contemporary research in autonomous driving has primarily focused on improving perception and planning subsystems to allow vehicles to better perceive and react to environmental uncertainties, but mostly in countries with well-maintained road infrastructures. Given that potholes are common structural road defects, an autonomous vehicle must be able to perceive and plan around potholes to avoid vehicular damage. This paper proposes an end-to-end pothole detection and avoidance system that runs in real-time consisting of an instance segmentation model running on a stereo camera and a path planner designed to execute four different maneuvers: (1) pothole avoidance, (2) alignment between the centers of the vehicle and the pothole, (3) deceleration and slowly passing over the pothole, and (4) stopping before the pothole. The overall system is deployed on an Intel Core i7-97 50H CPU laptop with an NVidia GTX 1650 GPU. All four maneuvers are executed on the NV-X1 platform, and experimental results demonstrate the proposed system's ability to segment pothole instances in 3D, plan an appropriate response maneuver, and successfully execute each maneuver. © 2025 IEEE.

关键词： Stereo image processing

来源：评论

学校读者我要写书评

暂无评论

Identifying Anomalous Edges with Link Sampling and Consensus 58

Identifying Anomalous Edges with Link Sampling and Consensus

引用

58th Asilomar Conference on Signals, Systems and computers, ACSSC 2024

作者： Karaaslanli, Abdullah Traganitis, Panagiotis A. Aviyente, Selin Michigan State University Department of Electrical and Computer Engineering East LansingMI United States

ISBN: (纸本)9798350354058

Graphs and graph structured data are ubiquitous in many applications as they readily represent datasets that lie in irregular, yet structured, domains. Due to their popularity, a plethora of methods have been developed to learn from graphstructured data, which have been shown to be effective in many real-world applications including biology, finance, and social sciences, among others. However, these methods generally assume that the observed graph is free of corruption. This assumption does not hold in cases where the graph includes structural contamination, such as anomalous edges, which can degrade learning performance. This paper presents a method to identify anomalous edges that can be employed prior to learning methods to mitigate their effects. The proposed method employs link prediction (LP) to assign likelihood scores to the observed edges. As LP is not anomaly aware, we combine LP with ideas from sampling and consensus algorithms. LP is applied to subgraphs which tend to have fewer anomalies. Edge anomaly scores are then obtained by judiciously combining LP prediction results across subgraphs. Preliminary results indicate the effectiveness of the proposed 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

Review of Various Failure Modes in High-Voltage Insulated Gate Bipolar Transistors During Short Circuit Operation 10

Review of Various Failure Modes in High-Voltage Insulated Ga...

引用

10th International Conference on Condition Monitoring and Diagnosis, CMD 2024

作者： Kim, Eunho Oh, Kwang Hoon Kim, Yong Sang Sungkyunkwan University Department of Electrical & Computer Engineering Kyunggi-Do Suwon-Si Korea Republic of

ISBN: (纸本)9788986510225

Insulated gate bipolar transistors (IGBTs) are widely used in various high-power applications such as consumer, industrial, renewable energy, and automotive areas owing to their easy gate driving and low switching and conduction losses. Power systems require IGBTs to withstand harsh operating conditions for system reliability. In this respect, IGBTs should have sufficient short circuit ruggedness until protection circuits activate and turn off IGBTs. This work aims to review various short circuit failure modes of IGBTs to understand failure mechanisms in more detail and thereby give better insights into the robust design of high-voltage IGBTs and their driving schemes. © 2024 The Korean Institute of electrical Engineers (KIEE).

关键词： Insulated gate bipolar transistors (IGBT)

来源：评论

学校读者我要写书评

暂无评论

Implementing Problem-Based and Experiential Learning for Undergraduate Students in Power Electronics Applied to Renewable Energy 54

Implementing Problem-Based and Experiential Learning for Und...

引用

54th IEEE Frontiers in Education Conference, FIE 2024

作者： González, Alanis M. Colón Ramírez, Valentina Ramírez Pérez, Marielys E. Quiñones Mojica, Isabel P. Rivera Vargas, José E. Crespo Cotto, Akim A. Pérez Rivera, Eduardo I. Ortiz University of Puerto Rico at Mayagüez Department of Electrical and Computer Engineering Mayaguez Puerto Rico

ISBN: (纸本)9798350351507

This full paper presents an innovative approach to undergraduate engineering education by integrating Problem-Based Learning (PBL) and Experiential Learning with traditional Lecture- Based Instruction to enhance student engagement and performance. The approach is exemplified through a project where undergraduate students develop a DC-AC inverter, control strategy, and learning experience. The objective is to bridge classroom theory with real-world application by having students design, simulate, and implement the inverter. This hands-on experience emphasizes careful consideration in choosing the appropriate topology, electronic components, and micro controller. The project illustrates how applying PBL and Experiential Learning helps students develop intuitive, creative, and critical thinking skills, addressing nuances that often go unnoticed in lecture-based learning. The paper highlights the benefits of this methodology, including improved problem-solving abilities, increased student engagement, and enhanced professional readiness. Additionally, it underscores the positive impact on workforce development and diversity, particularly through the involvement of female students in a traditionally male-dominated field. This approach not only enhances technical skills but also prepares students for advanced challenges in the field of power electronics, contributing to their academic and career trajectories. © 2024 IEEE.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Improving performance of deep learning models for 3D point cloud semantic segmentation via attention mechanisms

引用

computers and Graphics (Pergamon) 2022年 106卷 277-287页

作者： Vanian, Vazgen Zamanakos, Georgios Pratikakis, Ioannis Department of Electrical and Computer Engineering Democritus University of Thrace Xanthi67100 Greece

3D Semantic segmentation is a key element for a variety of applications in robotics and autonomous vehicles. For such applications, 3D data are usually acquired by LiDAR sensors resulting in a point cloud, which is a set of points characterized by its unstructured form and inherent sparsity. For the task of 3D semantic segmentation where the corresponding point clouds should be labeled with semantics, the current tendency is the use of deep learning neural network architectures for effective representation learning. On the other hand, various 2D and 3D computer vision tasks have used attention mechanisms which result in an effective re-weighting of the already learned features. In this work, we aim to investigate the role of attention mechanisms for the task of 3D semantic segmentation for autonomous driving, by identifying the significance of different attention mechanisms when adopted in existing deep learning networks. Our study is further supported by an extensive experimentation on two standard datasets for autonomous driving, namely Street3D and SemanticKITTI, that permit to draw conclusions at both a quantitative and qualitative level. Our experimental findings show that there is a clear advantage when attention mechanisms have been adopted, resulting in a superior performance. In particular, we show that the adoption of a Point Transformer in a SPVCNN network, results in an architecture which outperforms the state of the art on the Street3D dataset. © 2022 Elsevier Ltd

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

The Impact of SMOTE and ADASYN on Random Forest and Advanced Gradient Boosting Techniques in Telecom Customer Churn Prediction 10

The Impact of SMOTE and ADASYN on Random Forest and Advanced...

引用

10th International Conference on Web Research, ICWR 2024

作者： Imani, Mehdi Ghaderpour, Zahra Joudaki, Majid Beikmohammadi, Ali Stockholm University Department of Computer and System Sciences Stockholm10691 Sweden Ayatollah Boroujerdi University Electrical and Computer Engineering Boroujerd Iran University of Kashan Electrical and Computer Engineering Kashan Iran Stockholm University Department of Computer and Systems Sciences StockholmSE-16455 Sweden

ISBN: (纸本)9798350394986

This paper explores the capability of various machine learning algorithms, including Random Forest and advanced gradient boosting techniques such as XGBoost, LightGBM, and CatBoost, to predict customer churn in the telecommunications sector. For this analysis, a dataset available to the public was employed. The performance of these algorithms was assessed using recognized metrics, including Accuracy, Precision, Recall, F1-score, and the Receiver Operating Characteristic Area Under Curve (ROC AUC). These metrics were evaluated at different phases: subsequent to data preprocessing and feature selection;following the application of SMOTE and ADASYN sampling methods;and after conducting hyperparameter tuning on the data that had been adjusted by SMOTE and *** outcomes underscore the notable efficiency of upsampling techniques such as SMOTE and ADASYN in addressing the imbalance inherent in customer churn prediction. Notably, the application of random grid search for hyperparameter optimization did not significantly alter the results, which remained comparatively unchanged. The algorithms' performance post-ADASYN application marginally surpassed that observed after SMOTE application. Remarkably, LightGBM achieved an exceptional F1-score of 89% and an ROC AUC of 95% subsequent to the ADASYN sampling technique. This underlines the effectiveness of advanced boosting algorithms and upsampling methods like SMOTE and ADASYN in navigating the complexities of imbalanced datasets and intricate feature interdependencies. © 2024 IEEE.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

The design and analysis of an advanced hybrid renewable energy microgrid for Cyangugu Remote rural community in Rwanda using Homer Pro

The design and analysis of an advanced hybrid renewable ener...

引用

International Conference on Innovation and Technological Advances for Sustainability, ITAS 2023

作者： Asiegbu, Adimchinobi Almaktoof, Ali Adonis, Marco Electrical Electronics and Computer Engineering Department Cape Peninsula University of Technology Cape Town South Africa

ISBN: (纸本)9781032803722

In Rwanda, and in Cyangugu Remote community near the Kivu Lake, there is high solar sunshine energy, significant wind energy, abundant methane gas, appreciable geothermal energy, peat(biomass), hydro renewable energy sources, and grid power access. To ensure feasibility, accessibility, and sustainability, a balance need to be maintained to optimize this energy mix options, in terms of cost (NPV, COE etc.), maintenance, sensitivity, optimization, and other system parameters. The best combination of these Hybrid Renewable Energy Sources (HRES) considering the community’s energy needs, is modelled using the Hybrid Optimization of Multiple Electric Renewables – Professional (HOMER Pro), innovatively, to design and find out the proposed optimum system requirements with environmental advantages or benefits, best payback duration, lower or zero net GHGs and radiation emissions, performance optimization with lest value of Net Present Cost (NPC) and Cost of Energy (COE), sensitivity analysis involving components supply changes like wind speed change based atmospheric conditions, variable sunshine frequencies based on time of the day, seasons, fuel price changes etc. These seven energy supply components is used to provide access to modern, clean and reliable energy to Cyangugu. © 2025 The Author(s).

关键词： Clean energy

来源：评论

学校读者我要写书评

暂无评论

Joint Active and Passive Beamforming for NLOS Target Detection in RIS-Assisted Mono-Static Radar 58

Joint Active and Passive Beamforming for NLOS Target Detecti...

引用

58th Asilomar Conference on Signals, Systems and computers, ACSSC 2024

作者： Zeng, Cengcang Liang, Yifan Li, Hongbin Stevens Institute of Technology Department of Electrical and Computer Engineering HobokenNJ07030 United States

ISBN: (纸本)9798350354058

Reconfigurable intelligent surfaces (RIS) have gained widespread application in the field of communications and are gradually extending their utility to the radar domain. This paper focuses on a mono-static RIS-assisted radar system. The problem is to jointly design the active beamformer for the radar and passive beamformer for the RIS. We begin by introducing a general signal model. In order to enhance target illumination and echo reception, we maximize the received signal power through the optimization of both the radar beamformer and the phase-shift matrix for the RIS. We provide a closed-form solution for the resulting optimization problem. The proposed RIS-assisted radar is employed for non-line-of sight (NLOS) target detection, where the radar is obstructed from the target. A statistical analysis of the detection performance is presented. Simulation results underscore the significant impact of RIS size and radar-RIS distance on detection performance. Moreover, we demonstrate that RIS can offer a practical solution for NLOS target detection. © 2024 IEEE.

关键词： Beamforming

来源：评论

学校读者我要写书评

暂无评论

Feedback Communication Over the Binary Symmetric Channel with Sparse Feedback Times

Feedback Communication Over the Binary Symmetric Channel wit...

引用

2024 IEEE Global Communications Conference, GLOBECOM 2024

作者： Antonini, Amaael Wesel, Richard D. University of California Department of Electrical and Computer Engineering Los AngelesCA90095 United States

ISBN: (纸本)9798350351255

Posterior matching uses variable-length encoding controlled by noiseless feedback of the received symbols to achieve high rates for short average blocklengths. Traditionally, the feedback of a received symbol occurs before the next symbol is transmitted. The transmitter optimizes the next symbol transmission with full knowledge of every past received *** move posterior matching closer to practical communication, this paper limits how often feedback can be sent. We focus on reducing the frequency of the feedback while still maintaining the high rates that posterior matching achieves with feedback after every symbol. As it turns out, the frequency of the feedback can be reduced significantly with no noticeable reduction in rate. © 2024 IEEE.

关键词： Signal encoding

来源：评论

学校读者我要写书评

暂无评论

EQUIVARIANT SHAPE-CONDITIONED GENERATION OF 3D MOLECULES FOR LIGAND-BASED DRUG DESIGN 11

EQUIVARIANT SHAPE-CONDITIONED GENERATION OF 3D MOLECULES FOR...

引用

11th International Conference on Learning Representations, ICLR 2023

作者： Adams, Keir Coley, Connor W. Department of Chemical Engineering MIT United States Department of Electrical Engineering and Computer Science MIT United States

Shape-based virtual screening is widely used in ligand-based drug design to search chemical libraries for molecules with similar 3D shapes yet novel 2D graph structures compared to known ligands. 3D deep generative models can potentially automate this exploration of shape-conditioned 3D chemical space;however, no existing models can reliably generate geometrically realistic drug-like molecules in conformations with a specific shape. We introduce a new multimodal 3D generative model that enables shape-conditioned 3D molecular design by equivariantly encoding molecular shape and variationally encoding chemical identity. We ensure local geometric and chemical validity of generated molecules by using autoregressive fragment-based generation with heuristic bonding geometries, allowing the model to prioritize the scoring of rotatable bonds to best align the growing conformation to the target shape. We evaluate our 3D generative model in tasks relevant to drug design including shape-conditioned generation of chemically diverse molecular structures and shape-constrained molecular property optimization, demonstrating its utility over virtual screening of enumerated libraries. © 2023 11th International Conference on Learning Representations, ICLR 2023. All rights reserved.

关键词： Ligands

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：