This paper focuses on the survey of hardware-in-the-loop testing concepts of Multi-Agent systems for the microgrid. The role of agents in multi-agent systems is mainly performed by specialized microcontrollers. In thi...
详细信息
ISBN:
(纸本)9781728195100
This paper focuses on the survey of hardware-in-the-loop testing concepts of Multi-Agent systems for the microgrid. The role of agents in multi-agent systems is mainly performed by specialized microcontrollers. In this article, Raspberry Pi is used to implement control of various parts of the prototype of the microgrid. In the prototype, some of the microgrid devices can be implemented in hardware, and some in software. Such prototypes are widely used in the laboratories because of simply implementations and verification of control systems algorithms for distributed energy processes in private houses networks. The development own prototype is also presented in this paper.
Smart cities rely on large-scale heterogeneous distributedsystems known as Cyber-Physical systems (CPS). Information systems based on CPS typically analyse a massive amount of data collected from various data sources...
详细信息
ISBN:
(纸本)9781728172163
Smart cities rely on large-scale heterogeneous distributedsystems known as Cyber-Physical systems (CPS). Information systems based on CPS typically analyse a massive amount of data collected from various data sources that operate under noisy and dynamic conditions. How to determine the quality and reliability of such data is an open research problem that concerns the overall system safety, reliability and security. Our research goal is to tackle the challenge of real-time data quality assessment for large-scale CPS applications with a hybrid anomaly detection system. In this paper we describe the architecture of HADES, our Hybrid Anomaly DEtection System for sensors data monitoring, storage, processing, analysis, and management. Such data will be filtered with correlation-based outlier detection techniques, and then processed by predictive analytics for anomaly detection.
The problem of desining stabilizing decentralized controllers to achieve robust asymtotic traking of certain references despite certain disturbances, which is called as the decentralized robust servomecanism problem, ...
详细信息
ISBN:
(纸本)9781728198095
The problem of desining stabilizing decentralized controllers to achieve robust asymtotic traking of certain references despite certain disturbances, which is called as the decentralized robust servomecanism problem, is consdered for lineer time-invarant (LTI) systems with disributed timedelay. The formulation, however, allows the reprsentation of discrete and distributed time-delays together. It is asumed that, the references and the distrbance satisfy a LTI delaydiferential equation with distrubuted and/or discrete timedelays. The case of references and the disturbance satisfying a LTI diferential equation can also be treated. The necesary and suficient condtions for the solvbility of this problem are derived. The strcture of the controler, when a solution exists, is also presented.
In the news industry, as well as in social media, fake news detection and identification of news sources has become a central topic of discussion. In the era of digitization, anyone can easily generate or manipulate d...
详细信息
ISBN:
(纸本)9781728198668
In the news industry, as well as in social media, fake news detection and identification of news sources has become a central topic of discussion. In the era of digitization, anyone can easily generate or manipulate digital content and publish them on social media websites. On the one hand, these social networking platforms provide ample ease in modern-day communication but on the other hand, using such platforms has posed new challenges to real-world implementation like viral spreading of false/fake information with malicious intentions. In this paper, a naive blockchain and watermarking based social media framework is proposed to control the fake news propagation. We postulate a new blockchain model to mitigate existing challenges in this field. Moreover, the novel solution can help in reducing the spread of fake news by tracing the root or origin of the fake news on social media. Through our experimental results, we show that our blockchain-based solution is able to immediately stream data through a bloXroute server that can propagate data up to 100 times faster than conventional solutions.
B-mode ultrasound tongue imaging is a non-invasive and real-time method for visualizing vocal tract deformation. However, accurately extracting the tongue’s surface contour remains a significant challenge due to the ...
详细信息
ISBN:
(数字)9798350368741
ISBN:
(纸本)9798350368758
B-mode ultrasound tongue imaging is a non-invasive and real-time method for visualizing vocal tract deformation. However, accurately extracting the tongue’s surface contour remains a significant challenge due to the low signal-to-noise ratio (SNR) and prevalent speckle noise in ultrasound images. Traditional supervised learning models often require large labeled datasets, which are labor-intensive to produce and susceptible to noise interference. To address these limitations, we present a novel Counterfactual Ultrasound Anti-Interference Self-Supervised Network (CUAI-SSN), which integrates self-supervised learning (SSL) with counterfactual data augmentation, progressively disentangles confounding factors, ensuring that the model generalizes well across varied ultrasound conditions. Our approach leverages causal reasoning to decouple noise from relevant features, enabling the model to learn robust representations that focus on essential tongue structures. By generating counterfactual image-label pairs, our method introduces alternative, noise-independent scenarios that enhance model training. Furthermore, we introduce attention mechanisms to enhance the network’s ability to capture fine-grained details even in noisy conditions. Extensive experiments on real ultrasound tongue images demonstrate that CUAI-SSN outperforms existing methods, setting a new benchmark for automated contour extraction in ultrasound tongue imaging. Our code is publicly available at https://***/inexhaustible419/CounterfactualultrasoundAI.
We show how a high-performing, fully distributed and symmetric neural V-formation controller can be synthesized from a Centralized MPC (Model Predictive Control) controller using Deep Learning. This result is signific...
详细信息
ISBN:
(纸本)9781728172774
We show how a high-performing, fully distributed and symmetric neural V-formation controller can be synthesized from a Centralized MPC (Model Predictive Control) controller using Deep Learning. This result is significant as we also establish that under very reasonable conditions, it is impossible to achieve V-formation using a deterministic, distributed, and symmetric controller. The learning process we use for the neural V-formation controller is significantly enhanced by CEGkR, a Counterexample-Guided k-fold Retraining technique we introduce, which extends prior work in this direction in important ways. Our experimental results show that our neural V-formation controller generalizes to a significantly larger number of agents than for which it was trained (from 7 to 15), and exhibits substantial speedup over the MPC-based controller. We use a form of statistical model checking to compute confidence intervals for our neural V-formation controller's convergence rate and time to convergence.
The proceedings contain 202 papers. The topics discussed include: multi-relational graph convolutional networks for skeleton-based action recognition;identifying the right person in social networks with double metapho...
ISBN:
(纸本)9781665414852
The proceedings contain 202 papers. The topics discussed include: multi-relational graph convolutional networks for skeleton-based action recognition;identifying the right person in social networks with double metaphone codes;a novel strong cache consistency mechanism in ICN based on role division and lease model;demystifying the largest live game streaming platform via black-box measurement;framework-agnostic optimization of repeated skewed joins at massive scale;remote procedure call optimization of big data systems based on data awareness;MCSEC: secure coded matrix multiplication scheme for edge computing with minimum communication cost;low-rate DoS attack detection based on WPD-EE algorithm;user identity linkage across location-based social networks with spatio-temporal check-in patterns;optimizing 3-D placement of multiple UAVs based on Taguchi’s method;and feature envy detection based on Bi-LSTM with self-attention mechanism.
As the distributed System (DS) including Cloud computing is a congregation of geographically distributed and heterogeneous resources, the efficient scheduling of their resources requires a sound Resource Management Sy...
详细信息
ISBN:
(纸本)9781665417631
As the distributed System (DS) including Cloud computing is a congregation of geographically distributed and heterogeneous resources, the efficient scheduling of their resources requires a sound Resource Management System (RMS). The RMS requires the support of a sound Performance Prediction System (PPS). The performance prediction of resources is helpful for both Resource Management systems and users to make optimized resource usage decisions. There have been many PPS projects that span over several resources in several dimensions. Some of these PPS projects have been initiated for prediction of resources on the distributedsystems such as Grids, Clusters or Peer-Peer systems and therefore in a software engineering point of view, they are adaptable for the prediction of resources on the Clouds. In this paper the taxonomy for describing the PPS architecture is discussed. The taxonomy is used to categorize and identify approaches which are followed in the implementation of the existing PPSs for the distributedsystems such as Grids/ Clusters/ Peer-Peer and their adaptation in the Cloud computing. The taxonomy and the survey results can be used to identify approaches and issues that have not been fully explored in research.
In recent years, the rapid development of the shipping industry at sea has become an essential part of Chinas economic development. Large ships carry more items, and changes in temperature and humidity in the closed c...
详细信息
The proceedings contain 46 papers. The special focus in this conference is on Telecommunications, computing and Control. The topics include: Solving Multicriteria Optimization Problem for an Oil Refinery Plant;methods...
ISBN:
(纸本)9789813366312
The proceedings contain 46 papers. The special focus in this conference is on Telecommunications, computing and Control. The topics include: Solving Multicriteria Optimization Problem for an Oil Refinery Plant;methods and Techniques for Increasing the Accuracy of Continuous Non-invasive Blood Pressure Measurement Under Dynamic Loads;computer Modeling of Robust Control of Vibrationless Movement of Multi-mode Flexible Structures;feature-Based Plant Seedlings Classification;medical Training Simulation in Virtual Reality;application of the Hybrid Model to Numerical Modeling of the Urban Transport Network Topology;Synchronization Scheme for UWB Wireless sensor Network System;the Deep Survival Forest and Elastic-Net-Cox Cascade Models as Extensions of the Deep Forest;an Explanation Method for Siamese Neural Networks;detection and Prediction of Safety Faults in Inter-Device Networks Applying a Set of Data-Driven Methods;Hierarchical Multi-agent System for Production Control Using KPI Reconciliation;semi-supervised Learning for Medical Image Segmentation;developing a New Generation of Reconfigurable Heterogeneous distributed High Performance computing System;Usage of a BART Algorithm and Cognitive Services to Research Collaboration Platforms;a Computer-Aided Diagnosis System in the Diagnosis of Multiple Sclerosis;Predicting Students’ Performance on MOOC Using Data Mining Algorithms;on the Implementation of the Planar3D Model Using the Explicit Time Integration Scheme and the Statistical Front Tracking Method;fast Fourier Transform in Planar3D Model Using an Explicit Numerical Integration Scheme;employee Performance Analytics Approach Based on Anomaly Detection in User Activity;deep Predictive Control;development of an Algorithm for Determining the Railway Tracks on Video Image;on the Computational Complexity of Deep Learning Algorithms.
暂无评论