Detection and prediction of failures in Automated Guided Vehicles (AGV) are essential for the uninterrupted operation of production plants. Anomaly detection is usually achieved by comparing expected measurement value...
Detection and prediction of failures in Automated Guided Vehicles (AGV) are essential for the uninterrupted operation of production plants. Anomaly detection is usually achieved by comparing expected measurement values with actual observations. Thus, it is crucial to predict telemetry signals properly. In this paper, we research the prediction of energy consumption using state-of-the-art Artificial Neural Networks architectures (SCINet) compared with other Recurrent Neural Network (RNN) approaches on the data streams acquired from CoBotAGV. We especially focus on the possibility of applying feature weighting. We show that it can improve prediction capabilities. We also investigate resource utilization in terms of time to fit the embedded AGV environment.
Internet Background Radiation (IBR) comprises a range of unsolicited traffic directed towards Internet hosts. In general, this type of traffic is characterised by high levels of port scanning activity, malware propaga...
Internet Background Radiation (IBR) comprises a range of unsolicited traffic directed towards Internet hosts. In general, this type of traffic is characterised by high levels of port scanning activity, malware propagation, application exploits, system misconfiguration and denial-of-service attacks. IBR capture is typically undertaken by a system termed a network telescope. This records unfiltered incoming internet traffic for a specific CIDR block in the form of a packet capture (PCAP) file for analysis. This work proposes a novel, cloud-native approach to capturing IBR by the deployment of an ephemeral and reproducible architecture, described as code, distributed across all regions of a cloud service provider. In this paper we discuss the technical and financial viability of using a fleet of small-sized compute instances, in a spot price auction model, to maximise platform collection, capillarity and duration. We also present an overview analysis of the primary characteristics of IBR as collected during a month long proof-of-concept experiment across 26 regions of a cloud service provider in May 2023. Our analysis discusses the aspects of the dataset in quantitative terms: traffic aggregation per protocol, top TCP and UDP ports, top radiation sources and radiation distribution per cloud region. We also provide an overview of the most relevant threats detected. Our results include a formalisation and validation of the cloud telescope, with the corresponding supporting architecture described in Terraform and Ansible. The aggregate dataset amounted to 2.2 GB, and 21.8 million packets. Composition by protocol was 78% TCP, 14% ICMP and 8% UDP.
Machine Translation has played a critical role in reducing language barriers, but its adaptation for Sign Language Machine Translation (SLMT) has been less explored. Existing works on SLMT mostly use the Transformer n...
详细信息
ISBN:
(数字)9798350379495
ISBN:
(纸本)9798350379501
Machine Translation has played a critical role in reducing language barriers, but its adaptation for Sign Language Machine Translation (SLMT) has been less explored. Existing works on SLMT mostly use the Transformer neural network which exhibits low performance due to the dynamic nature of the sign language. In this paper, we propose a novel Gated-Logarithmic Transformer (GLoT) that captures the long-term temporal dependencies of the sign language as a time-series data. We perform a comprehensive evaluation of GloT with the transformer and transformer-fusion models as a baseline, for Sign-to-Gloss-to-Text translation. Our results demonstrate that GLoT consistently outperforms the other models across all metrics. These findings underscore its potential to address the communication challenges faced by the Deaf and Hard of Hearing community.
Proteins are complex biological information granules that play a crucial role in various cellular processes within living organisms. Processing 3D protein structures, which are the most informative from the biological...
详细信息
ISBN:
(数字)9798350362480
ISBN:
(纸本)9798350362497
Proteins are complex biological information granules that play a crucial role in various cellular processes within living organisms. Processing 3D protein structures, which are the most informative from the biological point of view, is both intricate and time-consuming. In particular, performing 3D protein structure searches against large protein datasets involves identifying similarities and conducting structural alignments across numerous molecules (granules). This task demands advanced methods for matching identical and similar regions within protein structures and substantial computational resources to handle large collections of macromolecular data efficiently. In this paper, we present our parallel implementation of scalable 3D structural alignment on the Apache Spark big data platform. We describe a customized approach that leverages Spark data transformations within the data processing pipeline for the alignment process. Our experimental results demonstrate that this solution, tightly integrated with the Spark processing model, is both efficient and scalable, even with the increasing volume of protein structure data.
A Peer-to-Peer (P2P) network consists of a large number of nodes, where each node may have different capabilities and properties. Finding peers with specific capabilities and properties is challenging. Thus, we propos...
详细信息
ISBN:
(数字)9781665480017
ISBN:
(纸本)9781665480024
A Peer-to-Peer (P2P) network consists of a large number of nodes, where each node may have different capabilities and properties. Finding peers with specific capabilities and properties is challenging. Thus, we propose a practical solution to the problem of peer discovery, which is finding peers in the network according to a specified query. We contribute a peer discovery for an m-ary tree-structured P2P network by utilizing a connected dominating set (CDS), a technique that is typically used in unstructured networks. Our approach of constructing the CDS requires no additional communication cost, while nodes can insert, update and remove data within ${\mathcal{O}}(1)$. Each node of the CDS – a dominating set node – maintains only a limited number of nodes. We confirm the properties of our proposed solution by using the ns-3 discrete-event simulator. This includes, besides the degree of decentralism of the peer discovery, also the heterogeneity of peers.
Chaos engineering is the discipline of injecting computing and network faults, such as increased network latency and unavailability of computing nodes, into an IT system to help developers in identifying problems that...
详细信息
ISBN:
(数字)9798350354232
ISBN:
(纸本)9798350354249
Chaos engineering is the discipline of injecting computing and network faults, such as increased network latency and unavailability of computing nodes, into an IT system to help developers in identifying problems that could arise in a production environment and tackle them. Several tools have emerged to ease the application of chaos engineering to complex IT systems, leveraging microservice and container-based applications deployed on Kubernetes. However, applying of such tools requires several phases to be put into practice, from defining a steady state to establishing an effective response plan if something goes wrong. To ease the application of chaos engineering in improving the resilience of Kubernetes applications, this work presents a smart scheduler for Kubernetes called TELKA: a Twin-Enhanced Learning for Kubernetes Applications, which combines chaos engineering, Digital Twin (DT), and Reinforcement Learning (RL) methodologies to mitigate the effects of computing and network faults. Instead of interacting directly with the physical Kubernetes application, TELKA learns by interacting with a digital twin, thus reducing the learning time and the operation costs related to the application of chaos engineering. Experiment results compare TELKA with other approaches to show its effectiveness in mitigating the adverse effects of injected faults.
With the growing Deaf and Hard of Hearing population worldwide and the persistent shortage of certified sign language interpreters, there is a pressing need for an efficient, signs-driven, integrated end-to-end transl...
详细信息
Image denoising has been used in various edge computing scenarios such as consumer electronics to improve the image quality and user experience. Existing image denoising methods based on Convolutional Neural Networks ...
详细信息
Zero-touch network is anticipated to inaugurate the generation of intelligent and highly flexible resource provisioning strategies where multiple service providers collaboratively offer computation and storage resourc...
详细信息
The rapid but uneven education development worldwide is creating many challenges. Changing conditions and rules in engineering fields such as programming, automation, and electronics are not always followed by changes...
The rapid but uneven education development worldwide is creating many challenges. Changing conditions and rules in engineering fields such as programming, automation, and electronics are not always followed by changes in education. Employers expect potential candidates to be current with the latest domain competencies and soft skills. The idea is to hire candidates with both knowledge (theoretical and practical) and experience in reflection and collaboration skills. Universities can not always keep up with the development of technology and the adaptation of curricula because change happens so quickly. Therefore, upgrades are needed in engineering education. Focusing education solely on measurable knowledge and results is a simple but often insufficient approach to presenting the entire curriculum within the time frame of a course. Our study of about 150 engineering students in Poland and Norway included the role of students' experiences in hands-on activities, especially labs. The research aimed to determine what students expect, what influences their results, and what complications may arise. The study results show that students often struggle with time management, prioritizing, and understanding practical tasks. In addition, there is a difference between students with and without practical work experience. Our research showed that both groups of students did not achieve all their intended educational goals for various reasons. Therefore, adapting the current teaching system to the student's needs and requirements is important.
暂无评论