Although the surveillance industry is growing due to increased concerns for public safety, traditional surveillance systems can be ineffective due to fixed positions, limited coverage, and the need for human operation...
详细信息
ISBN:
(数字)9798350330649
ISBN:
(纸本)9798350330656
Although the surveillance industry is growing due to increased concerns for public safety, traditional surveillance systems can be ineffective due to fixed positions, limited coverage, and the need for human operation. This paper proposes an edge computing surveillance system that can detect, track, and identify human presence using AI software. The system includes a video camera integrated into a structure that allows pan and tilt movements and a processing unit that performs all computations locally. The system can operate in two different modes, manual and automatic, and it can be controlled from a user-friendly web application. The manual mode allows the user to control the camera remotely, adjusting the position with buttons and handling additional functionalities like zoom. On the other hand, in automatic mode, the system detects people and identifies if they are an unknown subject or not. Identifications are recorded in an online log and the system takes pictures of unknown people to recognize recurrent intruders.
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 ...
详细信息
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.
This paper presents the creation of an innovative autonomous security robot designed to perform security functions with efficiency and reliability. The robot boasts mapping capabilities, which it utilizes to facilitat...
详细信息
ISBN:
(数字)9798350330649
ISBN:
(纸本)9798350330656
This paper presents the creation of an innovative autonomous security robot designed to perform security functions with efficiency and reliability. The robot boasts mapping capabilities, which it utilizes to facilitate autonomous patrol in designated areas. Its primary operations involve the use of computer vision to detect violence, identify weapons and dangerous items, and recognize individuals. Critical incidents are met with an immediate alarm and the subsequent transmission of data to a central security server, which then generates comprehensive reports displayed through a web application for security personnel. The application itself features remote control of the robot, incident report management, status updates, and incident analytics. The robot demonstrates substantial real-world application potential, particularly in crowded environments where it could outperform conventional surveillance. The project combines concepts of engineering, computer science, and cybersecurity, functioning per design but with considerable potential for future refinement and expansion, embodying the concept of an evolving technological solution.
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 ...
详细信息
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.
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...
详细信息
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.
Representation learning is a challenging, but essential task in audiovisual learning. A key challenge is to generate strong cross-modal representations while still capturing discriminative information contained in uni...
详细信息
Representation learning is a challenging, but essential task in audiovisual learning. A key challenge is to generate strong cross-modal representations while still capturing discriminative information contained in unimodal features. Properly capturing this information is important to increase accuracy and robustness in audiovisual tasks. Focusing on emotion recognition, this study proposes novel cross-modal ladder networks to capture modality-specific information while building strong cross-modal representations. Our method utilizes representations from a backbone network to implement unsupervised auxiliary tasks to reconstruct intermediate layer representations across the acoustic and visual networks. The skip connections between the cross-modal encoder and decoder provide powerful modality-specific and multimodal representations for emotion recognition. Our model on the CREMA-D corpus achieves high performance with precision, recall, and F1 scores over 80% on a six-class problem.
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. Conventi...
详细信息
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.
Ultrasonic waves provide an effective means of transmitting information through solid media, such as metal pipes and bars. However, the complex geometry of these materials causes reverberations that degrade the qualit...
详细信息
ISBN:
(数字)9798350371901
ISBN:
(纸本)9798350371918
Ultrasonic waves provide an effective means of transmitting information through solid media, such as metal pipes and bars. However, the complex geometry of these materials causes reverberations that degrade the quality of communication. In this paper, we propose denoising approaches using time reversal and inverse filtering methods for blind deconvolution. These methods enable significant improvements in signal-to-noise ratio (SNR), with the inverse filter demonstrating superior performance in both simulated and real-world scenarios. Our results show that this approach provides a robust solution for improving ultrasonic communication in complex solid channels.
This paper investigates an intelligent reflecting surface (IRS) aided millimeter-wave integrated sensing and communication (ISAC) system. Specifically, based on the passive beam scanning in the downlink, the IRS finds...
详细信息
Background Precise estimation of current and future comorbidities of patients with cardiovascular disease is an important factor in prioritizing continuous physiological monitoring and new *** learning(ML)models have ...
详细信息
Background Precise estimation of current and future comorbidities of patients with cardiovascular disease is an important factor in prioritizing continuous physiological monitoring and new *** learning(ML)models have shown satisfactory performance in short-term mortality prediction in patients with heart disease,whereas their utility in long-term predictions is *** study aimed to investigate the performance of tree-based ML models on long-term mortality prediction and effect of two recently introduced biomarkers on long-term *** This study used publicly available data from the Collaboration Center of Health Information Appli-cation at the Ministry of Health and Welfare,Taiwan,*** collected data were from patients admitted to the cardiac care unit for acute myocardial infarction(AMI)between November 2003 and September *** collected and analyzed mortality data up to December *** records were used to gather demo-graphic and clinical data,including age,gender,body mass index,percutaneous coronary intervention status,and comorbidities such as hypertension,dyslipidemia,ST-segment elevation myocardial infarction,and non-ST-segment elevation myocardial *** the data,collected from 139 patients with AMI,from medical and demographic records as well as two recently introduced biomarkers,brachial pre-ejection period(bPEP)and brachial ejection time(bET),we investigated the performance of advanced ensemble tree-based ML algorithms(random forest,AdaBoost,and XGBoost)to predict all-cause mortality within 14 years.A nested cross-validation was performed to evaluate and compare the performance of our developed models precisely with that of the conventional logistic regression(LR)as the baseline *** The developed ML models achieved significantly better performance compared to the baseline LR(C-Statistic,0.80 for random forest,0.79 for AdaBoost,and 0.78 for XGBoost,vs.0.77 for LR)(PRF<0.001,PAdaBoost<0.001,a
暂无评论