检索结果-内蒙古大学图书馆

International Conference on Machine Learning and Applications (ICMLA)

作者： Olaoluwa Adigun Bart Kosko Department of Electrical and Computer Engineering Signal and Image Processing Institute Los Angeles California

The new NoVa hidden neurons have outperformed ReLU hidden neurons in deep classifiers on some large image test sets. The NoVa or nonvanishing logistic neuron additively perturbs the sigmoidal activation function so that its derivative is not zero. This helps avoid or delay the problem of vanishing gradients. We here extend the NoVa to the generalized perturbed logistic neuron and compare it to ReLU and several other hidden neurons on large image test sets that include CIFAR-100 and Caltech-256. Generalized NoVa classifiers allow deeper networks with better classification on the large datasets. This deep benefit holds for ordinary unidirectional backpropagation. It also holds for the more efficient bidirectional backpropagation that trains in both the forward and backward directions.

关键词： Backpropagation Training Neurons Machine learning Delays Biological neural networks Logistics

来源：评论

学校读者我要写书评

暂无评论

Efficient Fault Detection in Nonlinear Industrial Process: A Reduced Kernel PCA-Based Spectral Clustering Approach

Efficient Fault Detection in Nonlinear Industrial Process: A...

引用

Artificial Intelligence, Applications, Innovation and Ethics (AI2E), International Conference for

作者： Khadija Attouri Majdi Mansouri Mansour Hajji Kais Bouzrara Laboratory of Advanced Materials and Nanotechnologies Higher Institute of Applied Sciences and Technology of Kasserine Kairouan University Tunisia Department of Electrical and Computer Engineering College of Engineering Sultan Qaboos University Muscat Oman Research Laboratory of Automation Signal Processing and Image National Engineering School of Monastir Tunisia

ISBN: (数字)9798331513733

ISBN: (纸本)9798331513740

The challenges posed by nonlinearities in industrial systems necessitate innovative techniques that outperform the limitations of traditional methods such as principal component analysis (PCA). While Kernel Principal Component Analysis (KPCA) offers a robust solution to handle nonlinear data, its computational requirements are a significant issue, especially for large-sized datasets. In this work, we propose a novel technique, namely, reduced kernel principal component analysis-based spectral clustering (RKPCA SpC ), to monitor and detect faults in the benchmark Tennessee Eastman process. The suggested approach addresses the complexity associated with KPCA by reducing data size during the model training phase. This reduction involves retaining only the principal components, preserving informative features, and selecting pertinent samples without compromising the original data's content. The efficacy of the proposed method is evaluated through key performance metrics, including false alarm rate (FAR), missed detection rate (MDR), detection time delay (DTD), and computation time (CT). Additionally, gained execution time (GET), gained storage space (GSP), and loss function (LF) are considered, providing a comprehensive assessment of the developed paradigms' effectiveness. The results demonstrate the promising capabilities of our proposed scheme.

关键词： Training Measurement Technological innovation Fault detection Delay effects Computational modeling Complexity theory Kernel Monitoring Principal component analysis

来源：评论

学校读者我要写书评

暂无评论

AI-Based Security Surveillance and Hazard Detection for Train Platform Safety

AI-Based Security Surveillance and Hazard Detection for Trai...

引用

IEEE International Conference on Electro-Information Technology

作者： Alvaro Aparicio Serna Xinrui Yu Jafar Saniie Department of Electrical and Computer Engineering Embedded Computing and Signal Processing (ECASP) Research Laboratory Illinois Institute of Technology Chicago IL U.S.A

ISBN: (数字)9798350330649

ISBN: (纸本)9798350330656

Safety in train platforms is a common concern in railway systems around the world. There are grave risks associated with the tracks and the crowds that often end up in injuries or deaths. Traditional approaches for ensuring safety in train transport networks rely on passive closed-circuit television (CCTV) monitorization that needs constant human attention. This paper proposes an AI-based alternative for detecting anomalies in surveillance videos, that is more efficient and cost-effective than traditional methods. Through Video Instance Segmentation (VIS), this work detects common risks such as overcrowding on the platform, people or objects standing on the edge of the platform, individuals or objects falling onto the tracks, the presence of firearms, and the presence of unattended baggage. The proposed algorithm combines state-of-the-art models like YOLOv8, ByteTrack, and Segment Anything Model (SAM) to classify, track, and segment object detections respectively. Additionally, this paper presents a custom-trained YOLOv8 model for gun detection. The results show that the system can successfully analyze video, create surveillance annotations, detect hazardous situations to alert authorities, and help prevent accidents and incidents on train platforms.

关键词： Instance segmentation Annotations Surveillance image edge detection Rail transportation Hazards Classification algorithms

来源：评论

学校读者我要写书评

暂无评论

Smart Multi-Building Energy Monitoring System

Smart Multi-Building Energy Monitoring System

引用

IEEE International Conference on Electro-Information Technology

作者： Saurabh Saluja Colin Prochnow Grant Couper Filip Zivko Xinrui Yu Mikhail Gromov Jafar Saniie Department of Electrical and Computer Engineering Embedded Computing and Signal Processing (ECASP) Research Laboratory Illinois Institute of Technology Chicago IL U.S.A.

ISBN: (数字)9798350330649

ISBN: (纸本)9798350330656

This paper presents an intelligent system for monitoring energy usage in smart buildings. It functions as a bridge between the smart grid and smart buildings. A web-based platform is designed to monitor sensor data and track power consumption on the grid. AI technology provides tips for energy conservation based on factors such as power usage patterns and weather conditions. The adaptability of our approach allows for the tuning of automated protocols based on evolving power usage patterns and grid conditions. Data is transmitted between the client devices and the central server via a Zigbee network organized in a star formation, allowing for mutual communication. Our implementation results in the improvement of the overall energy efficiency of supported infrastructure while ensuring continuous and optimized operation in case of a bulk grid blackout.

关键词： Smart buildings Energy conservation Zigbee Stars Smart homes Energy efficiency Smart grids

来源：评论

学校读者我要写书评

暂无评论

Basketball Video Analysis for Automated Game Data Acquisition Deep Learning

Basketball Video Analysis for Automated Game Data Acquisitio...

引用

IEEE International Conference on Electro-Information Technology

作者： Diego Rodriguez Garcia Xinrui Yu Jafar Saniie Department of Electrical and Computer Engineering Embedded Computing and Signal Processing (ECASP) Research Laboratory Illinois Institute of Technology Chicago IL U.S.A

ISBN: (数字)9798350330649

ISBN: (纸本)9798350330656

The utilization of data analytics to gain insights into the game of basketball has seen a remarkable surge in the past decade. Leagues such as the National Basketball Association are continuously exploring innovative methods to analyze game data, an approach that has significantly influenced the dynamics of the game. But to perform these analyses, a growing amount of data is needed, which is traditionally annotated by humans. This work proposes a 3-stage system able to automatically acquire relevant basketball game data from a broadcast video. The first stage is an object detector combined with a tracking algorithm to extract the main elements present in a basketball game video. Then, the players' visual information is analyzed to identify the players based on pixel color analysis and number recognition. Finally, a statistics generation algorithm assigns the game events to the corresponding player and team, so that the system can be used as an aid for box score annotation in major leagues, low-cost annotation in amateur games, or in-depth game video analysis.

关键词： Visualization Annotations image color analysis Data acquisition Optical character recognition Games Detectors

来源：评论

学校读者我要写书评

暂无评论

Advanced Robotic Surveillance for Urban Air Quality Safety

Advanced Robotic Surveillance for Urban Air Quality Safety

引用

IEEE International Conference on Electro-Information Technology

作者： Guillaume Hansen James R. Benson Muhammad Rafay Danish Khoa Truong Xinrui Yu Jafar Saniie Department of Electrical and Computer Engineering Embedded Computing and Signal Processing (ECASP) Research Laboratory Illinois Institute of Technology Chicago IL U.S.A.

ISBN: (数字)9798350330649

ISBN: (纸本)9798350330656

This paper presents a multifunctional quadruped robot, specifically engineered for comprehensive air quality monitoring and emergency assistance. Designed to navigate through urban environments, the robot autonomously collects and transmits real-time air quality data to a centralized database. This interdisciplinary paper integrates robotics, environmental science, and emergency response protocols to propose novel solutions for smart city infrastructure, public health, and disaster management. Specifically, this research highlights the critical role that autonomous systems play in monitoring environmental conditions and advancing safety protocols. This research leverages a comprehensive array of sensors including CO2 (MH-Z19), particle (SDS 011), GPS (ADA 746), DHT 22, MQ 9, and ADS 1115 converter, each meticulously implemented to ensure precise environmental data collection and analysis. Furthermore, the integration of cutting-edge technologies such as Robot Operating System (ROS), .NET MAUI, Python, and MariaDB establishes a robust framework for seamless operation, data processing, and secure storage within the quadruped robot system.

关键词： Temperature sensors Protocols Robot sensing systems Dynamic scheduling Sensors Quadrupedal robots Servers

来源：评论

学校读者我要写书评

暂无评论

Combining Relative and Absolute Learning Formulations to Predict Emotional Attributes From Speech

Combining Relative and Absolute Learning Formulations to Pre...

引用

IEEE Workshop on Automatic Speech Recognition and Understanding

作者： Abinay Reddy Naini Shruthi Subramanium Seong-Gyun Leem Carlos Busso Department of Electrical and Computer Engineering Multimodal Signal Processing (MSP) Laboratory The University of Texas at Dallas Richardson TX USA

Predicting absolute scores is the most common speech-emotion recognition (SER) task when predicting emotional attributes (i.e., valence, arousal, and dominance). However, studies have shown that emotion has an ordinal nature where it is more reliable to establish a preference between speech samples (e.g., one sample is more positive than the other). This paper pursues a novel direction to combine absolute and relative learning formulations for SER. The proposed multitask formulation can simultaneously estimate preference between speech samples and predict their absolute score, providing a flexible tool to analyze emotional content in speech. Both tasks mutually complement each other, allowing the model to outperform SER systems that are exclusively trained to either predict absolute scores or estimate preferences. The multitask weights can be set according to the intended applications, prioritizing one task while slightly compromising the performance of the other task.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Facial Recognition Attendance Tracking: An Intelligent Monitoring Approach

Facial Recognition Attendance Tracking: An Intelligent Monit...

引用

IEEE International Conference on Electro-Information Technology

作者： Syed Tauseeq Hussain Mario Antonio Nogueira Mansur Carvalho Vikrant Kishor Rathod Srinivasa Mani Sankar Reddy Karri Xinrui Yu Mikhail Gromov Jafar Saniie Department of Electrical and Computer Engineering Embedded Computing and Signal Processing (ECASP) Research Laboratory Illinois Institute of Technology Chicago IL U.S.A.

ISBN: (数字)9798350330649

ISBN: (纸本)9798350330656

This paper presents an Intelligent Monitoring System that utilizes the Internet of Things (IoT) and Artificial Intelligence (AI) technologies to automate the class attendance process reliably and efficiently. Conventional approaches for attendance tracking have been laborious and have consumed a significant amount of time, with errors and inconsistencies being a common occurrence. In contrast, the Intelligent Monitoring System combines object detection & recognition AI models, wireless communication, and cloud monitoring to generate reliable attendance data that can be used for various purposes, such as tracking student-by-student attendance data and monitoring overall attendance statistics. The system comprises an ID reader that uses radio frequency tags, a facial recognition system that uses a camera and AI algorithms, and a cloud monitoring system for attendance statistics. The proposed system is designed to overcome the challenges of traditional attendance-taking processes and provide a solution that is accurate, reliable, and efficient.

关键词： Wireless communication Cloud computing Face recognition Scalability Authentication Reliability engineering Security

来源：评论

学校读者我要写书评

暂无评论

Variation Bayesian Interference for Multiple Extended Targets or Unresolved Group Targets Tracking

arXiv

引用

arXiv 2024年

作者： Cheng, Yuanhao Cao, Yunhe Yeo, Tat-Soon Zhang, Yulin Jie, Fu National Laboratory of Radar Signal Processing Xidian University Xi’an710071 China Department of Electrical and Computer Engineering National University of Singapore 119077 Singapore

In this work, we propose a method for tracking multiple extended targets or unresolvable group targets in clutter environment. Firstly, based on the Random Matrix Model (RMM), the joint state of the target is modeled as the Gamma Gaussian Inverse Wishart (GGIW) distribution. Considering the uncertainty of measurement origin caused by the clutters, we adopt the idea of probabilistic data association and describe the joint association event as an unknown parameter in the joint prior distribution. Then the Variational Bayesian Inference (VBI) is employed to approximately solve the non-analytical posterior distribution. Furthermore, to ensure the practicability of the proposed method, we further provide two potential lightweight schemes to reduce its computational complexity. One of them is based on clustering, which effectively prunes the joint association events. The other is a simplification of the variational posterior through marginal association probabilities. Finally, the effectiveness of the proposed method is demonstrated by simulation and real data experiments, and we show that the proposed method outperforms current state-of-the-art methods in terms of accuracy and adaptability. Copyright © 2024, The Authors. All rights reserved.

关键词： Target tracking

来源：评论

学校读者我要写书评

暂无评论

Implementation of a Robust Chirplet signal Decomposition Algorithm on FPGA-SoC Platform for Ultrasonic Flaw Detection

Implementation of a Robust Chirplet Signal Decomposition Alg...

引用

IEEE International Symposium on Applications of Ferroelectrics (ISAF)

作者： Tianyang Fang Austin Fite Jafar Saniie Department of Electrical and Computer Engineering Embedded Computing and Signal Processing (ECASP) Research Laboratory Illinois Institute of Technology Chicago IL U.S.A.

ISBN: (数字)9798350371901

ISBN: (纸本)9798350371918

This research presents a robust chirplet decomposition algorithm designed for hardware implementation, specifically aimed at enhancing ultrasonic nondestructive testing and imaging. The study focuses on developing an algorithm and an FPGA hardware module that enable real-time chirplet decomposition, emphasizing increased processing speed while maintaining echo accuracy. A novel Maximum Likelihood Estimation (MLE)-based parameter estimation algorithm was developed to improve chirplet parameter estimation, enhancing both accuracy and convergence speed. This high-performance platform enables real-time ultrasonic imaging for flaw detection in steel specimens, demonstrating significant improvements in defect detection and characterization. The resultant platform has been tested against four alternative platforms to evaluate its effectiveness in enhancing execution times. Remarkably, when compared to similar embedded platforms, this speed-optimized platform achieves a 150-fold increase in processing speed, surpassing the next fastest embedded platform, the Teensy 4.0, which includes a Cortex-M7 processor operating at 600MHz. Additionally, when compared to an AMD Ryzen 7 3700X, this platform operates 6.6 times faster.

关键词： Parameter estimation Accuracy Ultrasonic imaging Chirp signal processing algorithms Transforms Hardware Acoustics Real-time systems Steel

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：