Most of the recent researches related to hybrid traffic scheduling in Time-Sensitive Networking (TSN) focus on how to ensure bounded low-delay transmission for Scheduled Traffic (ST) and Stream Reservation (SR) traffi...
详细信息
ISBN:
(纸本)9781665450867
Most of the recent researches related to hybrid traffic scheduling in Time-Sensitive Networking (TSN) focus on how to ensure bounded low-delay transmission for Scheduled Traffic (ST) and Stream Reservation (SR) traffic. However, if high-priority traffic blocks Best Effort (BE) traffic represented by data logging and periodic software updates for a long time, the end-to-end delay of BE messages will be too large. To reduce the blocking of SR traffic on BE traffic by reducing the reserved bandwidth for SR traffic, this paper proposes a traffic scheduling algorithm combined with ingress shaping. First, add ingress buffers before SR queues. Then, schedule SR traffic on a per-flow basis in the TSN switch by limiting the rate at which frames in each ingress buffer enter the SR queue. Finally, joint egress shaping and ingress shaping to reserve bandwidth resources that match its delay requirement for each SR flow. Simulation results show that the maximum end-to-end delay of BE messages can be reduced by 0.32%~17.19%.
The evolution of embedded systems has demonstrated their reliability as a solution for monitoring and controlling industrial systems, particularly in renewable energy conversion systems like photovoltaic (PV) energy. ...
详细信息
ISBN:
(数字)9798350373974
ISBN:
(纸本)9798350373981
The evolution of embedded systems has demonstrated their reliability as a solution for monitoring and controlling industrial systems, particularly in renewable energy conversion systems like photovoltaic (PV) energy. The increasing adoption of PV systems highlights the critical need for effective fault diagnosis to ensure their reliable operation. In this paper, we present a novel fault diagnosis approach utilizing Long Short-Term Memory (LSTM) networks optimized through Bayesian optimization techniques. Our methodology is implemented on a Raspberry Pi platform, demonstrating the feasibility of deploying sophisticated fault diagnosis algorithms in resource-constrained environments. Through extensive experiments, we demonstrate the effectiveness of our approach to accurately diagnose faults in grid-connected photovoltaic systems, thereby improving the reliability and efficiency of integrated environmental monitoring *** obtained results highlight the potential of combining advanced deep learning techniques with embedded systems to address complex diagnostic challenges, as demonstrated by achieving a 100% accuracy rate.
This paper introduces a theoretically-rigorous sound source localization (SSL) method based on a robust extension of the classical multiple signal classification (MUSIC) algorithm. The original SSL method estimates th...
详细信息
ISBN:
(数字)9789082797091
ISBN:
(纸本)9781665467995
This paper introduces a theoretically-rigorous sound source localization (SSL) method based on a robust extension of the classical multiple signal classification (MUSIC) algorithm. The original SSL method estimates the noise eigenvectors and the MUSIC spectrum by computing the spatial covariance matrix of the observed multichannel signal and then detects the peaks from the spectrum. In this work, the covariance matrix is replaced with the positive definite shape matrix originating from the elliptically contoured $\alpha$ -stable model, which is more suitable under real noisy high-reverberant conditions. Evaluation on synthetic data shows that the proposed method outperforms baseline methods under such adverse conditions, while it is comparable on real data recorded in a mild acoustic condition.
The increasing prevalence of psychological stress in modern society necessitates the development of effective monitoring and classification systems. This paper presents the design and implementation of the acquisition...
详细信息
ISBN:
(数字)9798350364637
ISBN:
(纸本)9798350364644
The increasing prevalence of psychological stress in modern society necessitates the development of effective monitoring and classification systems. This paper presents the design and implementation of the acquisition system for the bio-signal measurement. The proposed system utilizes a combination of sensors and a microcontroller to collect and analyze physiological data indicative of stress levels. The bio-signals data monitored include heart rate, pulse rate, galvanic skin response, body temperature, and acceleration. The data acquisition process is managed by a microcontroller, which processes the raw signals and transmits them to a central processing unit for further analysis. The built system captures the acquired data in real time, offering immediate feedback and long-term monitoring capabilities. The system operates on a small power supply of 5V and 250mA, featuring a modular and portable design for ease of use. This approach aims to offer a cost-effective, non-invasive solution for early detection and management of psychological stress, contributing to improved mental health outcomes. Experimental results demonstrate the system's accuracy and reliability in acquiring and processing bio-signal data. These results represent preliminary research, with future work focusing on integrating advanced data analysis techniques and machine learning algorithms to enhance stress classification and prediction, expanding the system's applicability in clinical and everyday settings.
This project aims to identify liver tumors using deep learning techniques. The core of our approach is a sophisticated neural network trained on real CT scans of patients with liver tumors. By leveraging advanced sign...
详细信息
ISBN:
(数字)9798331540364
ISBN:
(纸本)9798331540371
This project aims to identify liver tumors using deep learning techniques. The core of our approach is a sophisticated neural network trained on real CT scans of patients with liver tumors. By leveraging advancedsignal-processingalgorithms and deep learning models, our AI method accurately distinguishes between tumors and healthy liver tissue. Accurate identification of liver tumors on CT images is crucial for planning effective radiation therapy. CT and MRI scans provide detailed images of the internal structure of the body by analyzing tissues. Our primary objective is to develop an AI-driven neural network that can reliably identify liver tumors in these images. Given the variability in liver location among individuals, our approach employs specific techniques to ensure precision. Using U-net technology, our goal is to enhance the speed and accuracy of tumor identification, thereby improving patient access to timely and accurate diagnoses. This project underscores the significant potential of deep learning applications in health care.
In practice, hands-free devices commonly employ low-cost electronic components. Unfortunately, the nonlinear distortion arising from them affects the performance of acoustic echo cancellers. To address this issue, thi...
详细信息
ISBN:
(数字)9789082797091
ISBN:
(纸本)9781665467995
In practice, hands-free devices commonly employ low-cost electronic components. Unfortunately, the nonlinear distortion arising from them affects the performance of acoustic echo cancellers. To address this issue, this paper proposes a new adaptive filtering algorithm based on nonlinear acoustic echo cancellation (NAEC) framework for improving its echo cancellation performance. The advanced method employs a novel combination of an adaptive filter based on sub-filter and proportionate adaptation, and presents an enhanced NAEC framework. In addition to that, both convergence and steady-state analysis of the proposed NAEC algorithm are presented. The performance evaluation made in the presence of speech and colored noise inputs has shown an average improvement of 3–4 dB compared to the existing algorithms.
The prime idea is to propose an effective compression technique obtaining improved PSNR and better compression ratio (CR) with Curvelet transformation technique and encoding the multi-wavelet parameters using Set Part...
详细信息
This study presents an embedded system (ES) designed for fault detection and diagnosis in grid-connected photovoltaic (GCPV) systems using transient regime analysis. The primary aim of transient regime analysis is to ...
详细信息
ISBN:
(数字)9798350373974
ISBN:
(纸本)9798350373981
This study presents an embedded system (ES) designed for fault detection and diagnosis in grid-connected photovoltaic (GCPV) systems using transient regime analysis. The primary aim of transient regime analysis is to facilitate real-time decision-making, especially during critical faults. A neural network classifier, incorporating a Genetic Algorithm for automated hyperparameter optimization, is developed for GCPV fault classification. These classifiers are seamlessly integrated into a Raspberry Pi 4 platform for fault diagnosis in GCPV systems. Both simulation and experimental results substantiate the ES's viability for fault diagnosis in the examined GCPV system, achieving high accuracy and enabling prompt decision-making to enhance the reliability and safety of GCPV systems.
Breast cancer remains to be one of the most common cancers throughout the world. Detection of mammographically occult breast cancer is a trivial process due to hidden tumours in women with dense breasts. Data augmenta...
详细信息
ISBN:
(纸本)9781665476485
Breast cancer remains to be one of the most common cancers throughout the world. Detection of mammographically occult breast cancer is a trivial process due to hidden tumours in women with dense breasts. Data augmentation techniques are in demand due to existing paucity in the dash images that are labeled. In this brief, a model for the detection of mammographically occult breast cancer is developed with pix2pix Generative Adversarial Networks (GAN) as in imperative tool for data augmentation. In this work, GANs are used to construct transformations of original images in the dataset. The U-net based of CNN layers is used to preserve long-range connections in wide neighbourhoods to provide a balanced partitioning. For the cancer detection, this model can be used as an individual layer in a Convolutional neural network (CNN). Upon comparison with transfer learning approach, the proposed approach has higher accuracy for two VGG-16 and Resnet-50 CNNs.
TV Datacenter is the primary storage facility where servers for data storage are located. TV Datacenters have exploded in popularity over the last decade, becoming the epicenter of the technical landscape. As the size...
详细信息
ISBN:
(纸本)9781665480772
TV Datacenter is the primary storage facility where servers for data storage are located. TV Datacenters have exploded in popularity over the last decade, becoming the epicenter of the technical landscape. As the size and ability of the centers grow, the complexity in managing them grows as well. The information and functionality grid are in danger of imploding, with potentially catastrophic consequences. As a result, solutions that can keep pace with the growth of data delivery, as well as Datacenter storage sizes, are needed. The main objective behind this research study is to propose a complete and advanced system for accommodating the enlargement of Datacenters, for enhancing data delivery in Datacenters, and for detection of errors and problems in TV Datacenters. Moreover, the system will also perform advanced and robust monitoring of TV Datacenters. The significance of the study relies on the algorithms that are proposed since these algorithms are completely novel as well as they are highly performant. In addition, these algorithms incorporate new technologies of image processing. The results obtained using the algorithms showed a detection rate obtained of 83.33% which can be considered to be an indicator of the high performance of the proposed detection system. Moreover, according to the results, the minimum time of replacement is zero seconds meaning that the replacement was done automatically after the detection of the corruption in the video. The results also showed that for all videos, the detected number of frames were all successfully replaced. The frame replacement showed 100% efficiency for every video.
暂无评论