检索结果-内蒙古大学图书馆

23rd IEEE International Conference on Machine Learning and Applications, ICMLA 2024

作者： Cordova, Jonathan Jiang, Xunfei Jia, Xudong Li, Bingbing California State University Department of Computer Science NorthridgeCA91330 United States College of Engineering and Computer Science California State University NorthridgeCA91330 United States California State University Department of Manufacturing Systems Engineering and Management NorthridgeCA91330 United States

ISBN: (纸本)9798350374889

Vehicle detection and classification are important for intelligent transportation planning, directly impacting traffic flow and management efficiency. There have been a lot of research on vehicle detection and classification for autonomous driving, but research on roadside traffic flow has not been fully investigated. This research explores various methods for vehicle detection and classification that could be applied to 3D roadside traffic flow analysis. Using data collected from a Velodyne 32C Lidar sensor 3D camera and a stereo-based depth 2D camera, this project implemented a Complex-YOLO projection-based model, by converting 3D point cloud data into a 2D bird-eye-view projection and applying the YOLO model for vehicle detection and classification. Our experimental results demonstrated that using transfer learning as a training technique, along with normalization of the rotation angle, enhanced the model performance for vehicle detection and classification. Without normalization of the rotation angle, the highest precision achieved was 89.71 %, with a recall of 85.15 %. With normalization of the rotation angle, the best model achieved a precision of 92.20 % with a recall of 84.90 %, demonstrating the effectiveness of both transfer learning and normalization in handling and aligning the dataset for more effective learning. © 2024 IEEE.

关键词： Vehicle detection

来源：评论

学校读者我要写书评

暂无评论

SMART-WRITE: Adaptive Learning-Based Write Energy Optimization for Phase Change Memory 15

SMART-WRITE: Adaptive Learning-Based Write Energy Optimizati...

引用

15th IEEE Annual Computing and Communication Workshop and Conference, CCWC 2025

作者： Desai, Mahek Quinn, Rowena Asadinia, Marjan California State University Computer Science Department Northridge United States Illinois Central College Computer Science Department Peoria United States

ISBN: (纸本)9798331507695

As dynamic random access memory (DRAM) and other current transistor-based memories approach their scalability limits, the search for alternative storage methods becomes increasingly urgent. Phase-change memory (PCM) emerges as a promising candidate due to its scalability, fast access time, and zero leakage power compared to many existing memory technologies. However, PCM has significant drawbacks that currently hinder its viability as a replacement. PCM cells suffer from a limited lifespan because write operations degrade the physical material, and these operations consume a considerable amount of energy. For PCM to be a practical option for data storage-which involves frequent write operations-its cell endurance must be enhanced, and write energy must be reduced. In this paper, we propose SMART-WRITE, a method that integrates neural networks (NN) and reinforcement learning (RL) to dynamically optimize write energy and improve performance. The NN model monitors real-time operating conditions and device characteristics to determine optimal write parameters, while the RL model dynamically adjusts these parameters to further optimize PCM's energy consumption. By continuously adjusting PCM write parameters based on real-time system conditions, SMART-WRITE reduces write energy consumption by up to 63% and improves performance by up to 51% compared to the baseline and previous models. © 2025 IEEE.

关键词： Scalability

来源：评论

学校读者我要写书评

暂无评论

A Real-Time Traffic Monitoring System Based on YOLOv8 for Vehicle Detection and Classification

A Real-Time Traffic Monitoring System Based on YOLOv8 for Ve...

引用

2024 IEEE International Conference on Green Energy and Smart Systems, GESS 2024

作者： Castillo, Jimwell Rosculete, Robin Babayans, Raymond Gharapeti Merzoian, Anthony Groves, Kaylee Calva, Gisela Dollente, Alma Jia, Xudong Li, Bingbing Jiang, Xunfei California State University Department of Computer Science NorthridgeCA91330 United States College of Engineering and Computer Science California State University NorthridgeCA91330 United States California State University Department of Manufacturing Systems Engineering and Management NorthridgeCA91330 United States

ISBN: (纸本)9798350379617

Urban traffic congestion presents significant challenges that require efficient and intelligent management solutions. Traditional traffic monitoring methods lack precision and adapt-ability, especially under varying conditions. Our project aims to develop a real-time traffic monitoring system using 2D camera technology and machine learning algorithms to address these gaps. The system includes a camera array for data collection, a data processing unit, and a user interface for real-time monitoring. Our solution employs YOLOv8 for accurate vehicle detection and classification and is demonstrated through rigorous testing. The system offers a robust framework for enhancing urban traffic management, reducing congestion, and improving road safety. Experimental results highlight the system's effectiveness in data aggregation, storage, and real-time processing. © 2024 IEEE.

关键词： Traffic congestion

来源：评论

学校读者我要写书评

暂无评论

Deep Learning Approach for Incongruous Data: Dataset Matters 23

Deep Learning Approach for Incongruous Data: Dataset Matters

引用

23rd International Conference on Machine Learning and Cybernetics, ICMLC 2024

作者： Torabinejad, Tina Sood, Kanika College of Engineering and Computer Science California State University FullertonCA92831 United States California State University Faculty of College of Engineering and Computer Science FullertonCA92831 United States

ISBN: (纸本)9798331528041

Today, humans seek opportunities to grow professionally and improve their mental health. As a result, anxiety and depression are now prominent to the point that people often accept them as part of their usual regular life routine. According to the World Health Organization (WHO), more than 300 million people around the world are suffering from depression and anxiety disorder. Therefore, being able to detect risk factors that lead to depression can be beneficial to the healthcare system. We use machine learning techniques to detect depression risk factors using a medical survey dataset, the Behavioral Risk Factor Surveillance System (BRFSS), available from the Centers for Disease Control and Prevention (CDC). This survey is obtained explicitly through telephone calls from adults 18 years and older who live in the United states of America. Oversampling and undersampling techniques and eight machine learning techniques are used to evaluate further and examine the data set. Among all, the SMOTE oversampling techniques show enhanced performance over the undersampling and no sampling techniques, and the deep neural network generates the best outcome compared to other techniques. © 2024 IEEE.

关键词： Disease control

来源：评论

学校读者我要写书评

暂无评论

Spatio-temporal Graph-Based Generation and Detection of Adversarial False Data Injection Evasion Attacks in Smart Grids

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2024年第12期5卷 6601-6616页

作者： Takiddin, Abdulrahman Ismail, Muhammad Atat, Rachad Serpedin, Erchin Florida State University Department of Electrical and Computer Engineering FAMU-FSU College of Engineering TallahasseeFL32310 United States Tennessee Tech University Department of Computer Science CookevilleTN38505 United States Lebanese American University Department of Computer Science and Mathematics Beirut1102-2801 Lebanon Texas A&M University Department of Electrical and Computer Engineering College StationTX77843 United States

Smart power grids are vulnerable to security threats due to their cyber-physical nature. Existing data-driven detectors aim to address simple traditional false data injection attacks (FDIAs). However, adversarial false data injection evasion attacks (FDIEAs) present a more serious threat as adversaries, with different levels of knowledge about the system, inject adversarial samples to circumvent the grid's attack detection system. The robustness of state-of-the-art graph-based detectors has not been investigated against sophisticated FDIEAs. Hence, this article answers three research questions. 1) What is the impact of utilizing spatio-temporal features to craft adversarial samples and how to select attack nodes? 2) How can adversaries generate surrogate spatio-temporal data when they lack knowledge about the system topology? 3) What are the required model characteristics for a robust detection against adversarial FDIEAs? To answer the questions, we examine the robustness of several detectors against five attack cases and conclude the following: 1) Attack generation with full knowledge using spatio-temporal features leads to 5%-26% and 2%-5% higher degradation in detection rate (DR) compared to traditional FDIAs and using temporal features, respectively, whereas centrality analysis-based attack node selection leads to 3%-11% higher degradation in DR compared to a random selection;2) Stochastic geometry-based graph generation to create surrogate adversarial topologies and samples leads to 3%-13% higher degradation in DR compared to traditional FDIAs;and 3) Adopting an unsupervised spatio-temporal graph autoencoder (STGAE)-based detector enhances the DR by 5-53% compared to benchmark detectors against FDIEAs. © 2020 IEEE.

关键词： Cyber attacks

来源：评论

学校读者我要写书评

暂无评论

Game Theory Meets Data Augmentation

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2024年第12期5卷 6080-6094页

作者： Kang, Yuhan Zare, Samira Lin, Alex Tong Han, Zhu Osher, Stanley Nguyen, Hien Van Department of Electrical and Computer Engineering University of Houston HoustonTX77004 United States University of California Department of Mathematics Los AngelesCA90095 United States University of Houston Department of Electrical and Computer Engineering HoustonTX77004 United States Kyung Hee University Department of Computer Science and Engineering Seoul446-701 Korea Republic of

Data augmentation is a critical component in building modern deep-learning systems. In this article, we propose MFG Augment, a novel data augmentation method based on the mean-field game (MFG) theory that can synthesize a sequence of data between every two images or features. The central idea is to consider every image as a distribution over its pixel or feature space. Using MFG theory, we can generate a time-continuous "path"from one distribution to another so that the points along the "path"are augmented images or features. Empirically, the experiment results on MNIST, CIFAR-10, and ImageNet demonstrate that the proposed technology has better generalization ability and higher classification accuracy as compared to several benchmark methods. More importantly, our MFG Augment improves the test accuracy significantly when the dataset size is small. MFG Augment consistently shows better affinity and diversity scores, two important empirical metrics for evaluating the generalization of data augmentation techniques. © 2020 IEEE.

关键词： Game theory

来源：评论

学校读者我要写书评

暂无评论

Transfer Learning Enhanced Deep Reinforcement Learning for Volt-Var Control in Smart Grids

Transfer Learning Enhanced Deep Reinforcement Learning for V...

引用

2025 IEEE PES Grid Edge Technologies Conference and Exposition, Grid Edge 2025

作者： Kumar, Kundan Ravikumar, Gelli Iowa State University Department of Computer Science and Electrical and Computer Engineering IA50010 United States

ISBN: (纸本)9798350352528

The integration of renewable energy resources has made power system management increasingly complex. DRL is a potential solution to optimize power system operations, but it requires significant time and resources during training. The control policies developed using DRL are specific to a single grid and require retraining from scratch for other grids. Training the DRL model from scratch is computationally expensive. This paper proposes a novel TL with a DRL framework to optimize VV C across different grids. This framework significantly reduces training time and improves VVC control performance by fine-tuning pre-trained DRL models for various grids. We developed a policy reuse classifier that transfers the knowledge from the IEEE-123 Bus system to the IEEE-13 Bus system. We performed an impact analysis to determine the effectiveness of TL. Our results show that TL improves the VVC control policy by 69.51 %, achieves faster convergence, and reduces the training time by 98.14%. © 2025 IEEE.

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

StraightLine: An End-to-End Resource-Aware Scheduler for Machine Learning Application Requests 3

StraightLine: An End-to-End Resource-Aware Scheduler for Mac...

引用

3rd International Conference on Artificial Intelligence, Internet of Things and Cloud Computing Technology, AIoTC 2024

作者： Ching, Cheng-Wei Guan, Boyuan Xu, Hailu Hu, Liting University of California Santa Cruz Department of Computer Science and Engineering Santa CruzCA United States Center of Florida International University MiamiFL United States California State University Department of Computer Engineering and Computer Science Long BeachCA United States

ISBN: (纸本)9798331530280

The life cycle of machine learning (ML) applications consists of two stages: model development and model deployment. However, traditional ML systems (e.g., training-specific or inference-specific systems) focus on one particular stage or phase of the life cycle of ML applications. These systems often aim at optimizing model training or accelerating model inference, and they frequently assume homogeneous infrastructure, which may not always reflect real-world scenarios that include cloud data centers, local servers, containers, and serverless platforms. We present StraightLine, an end-to-end resource-aware scheduler that schedules the optimal resources (e.g., container, virtual machine, or serverless) for different ML application requests in a hybrid infrastructure. The key innovation is an empirical dynamic placing algorithm that intelligently places requests based on their unique characteristics (e.g., request frequency, input data size, and data distribution). In contrast to existing ML systems, StraightLine offers end-to-end resource-aware placement, thereby it can significantly reduce response time and failure rate for model deployment when facing different computing resources in the hybrid infrastructure. © 2024 IEEE.

关键词： Resource allocation

来源：评论

学校读者我要写书评

暂无评论

Racially Inclusive Approach to Facial Beauty Modeling Using Machine Learning

Racially Inclusive Approach to Facial Beauty Modeling Using ...

引用

2024 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2024

作者： Nguyen, Erik Akwafuo, Sampson Bein, Doina Ojeme, Blessing California State University Fullerton Department of Computer Science Fullerton United States Morgan State University Department of Computer Science BaltimoreMD United States

ISBN: (纸本)9798350386226

Facial beauty perception is a complex area of study that has intrigued researchers across various disciplines. While some argue that it is subjective, influenced by personal and cultural factors, others propose that it is objective and rooted in evolutionary biology. This study explores the latter perspective, aiming to model facial beauty with an emphasis on racial fairness. Departing from black box convolutional deep learning approaches that are susceptible to racial biases, particularly arising from their holistic consideration of facial attributes such as skin tone, our focus lies solely on designing a more transparent machine learning model that integrates guardrails to prevent the introduction of such biases. By deliberately excluding skin tone and selecting specific features for the model to learn from, we aim to ensure a more equitable assessment across diverse racial and ethnic groups. Following rigorous training and evaluation, our hybrid model demonstrated impressive predictive performance, despite prioritizing transparency and racial fairness over complexity. © 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

Transfer learning with ResNet50 for malicious domains classification using image visualization

引用

Discover Artificial Intelligence 2024年第1期4卷 52页

作者： Demmese, Fikirte Ayalke Shajarian, Shaghayegh Khorsandroo, Sajad Department of Computer Science College of Engineering North Carolina Agricultural and Technical State University GreensboroNC United States

The Internet has become a vital part of our daily lives, serving as a hub for global connectivity and a facilitator for seamless communication and information exchange. However, the rise of malicious domains presents a serious challenge, undermining the reliability of the Internet and posing risks to user safety. These malicious activities exploit the Domain Name System (DNS) to deceive users, leading to harmful activities such as spreading drive-by-download malware, operating botnets, creating phishing sites, and sending spam. In response to this growing threat, the application of Machine Learning (ML) techniques has proven to be highly effective. These methods excel in quickly and accurately detecting, classifying, and analyzing such threats. This paper explores the latest developments in using transfer learning for the classification of malicious domains, with a focus on image visualization as a key methodological approach. Our proposed solution has achieved a remarkable testing accuracy rate of 98.67%, demonstrating its effectiveness in detecting and classifying malicious domains. © The Author(s) 2024.

关键词： Image classification

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：