This paper presents the ability of the federated learning concept to create a collaboration between multiple devices using a shared global model, while still keeping data privacy to meet the General Data Protection Re...
This paper presents the ability of the federated learning concept to create a collaboration between multiple devices using a shared global model, while still keeping data privacy to meet the General Data Protection Regulation (GDPR). In real-world application scenarios, this concept faces problems related to the defense of the global model from possible attacks and the compatibility with non-independent and identically distributed data (non-IID). This paper presents two aggregation algorithms compatible with non-IID data, which use a refined aggregation of the local model, based on their accuracy. Thus, the proposed algorithms can refine the confidence in each client, eliminate intruders and allow a safe aggregation of the global model. Testing scenarios performed for IID and non-IID data illustrate that the proposed algorithms are able to provide faster training and improved robustness against intruders, w.r.t. the well-known federated average algorithm.
Automated Ground Vehicles (AGVs) use deep-learning-based vision systems to perceive the surrounding environment and extract relevant information about it. Although deep learning models offer high capabilities, they re...
详细信息
In multimodal optimization, it is important to obtain all the optima in a single run, for an insightful description of the potential design configurations. Genetic algorithms, as population-based approaches, are very ...
详细信息
This paper describes the idea of novel approach to creating an expert system for partial discharge (PD) assessment in power transformers. The proposed system is intended to support the decision-making process regardin...
详细信息
Digital control of product-on-pallet distribution is organized on two layers in logistics systems: the low-level local process automation and the supervision and coordination dual logistic execution system. The paper&...
详细信息
During the last few years, there has been a growing interest in the topic of using natural or synthetic esters as an alternative to mineral oils in oil transformers due to the easier way to obtain them and their abili...
During the last few years, there has been a growing interest in the topic of using natural or synthetic esters as an alternative to mineral oils in oil transformers due to the easier way to obtain them and their ability to exhibit better electrical properties. In addition, more and more researchers are describing in their work that doping esters with nanoparticles is capable of further improving these properties. Therefore, in the current work, it was decided to see what effect the addition of a hydrophobic carbon shell iron nanoparticle to ORLEN mineral oil and Midel 7131 synthetic ester would have on selected electrical parameters of the insulating fluid, i.e. breakdown voltage and electrical strength.
The article deals with methods of usability testing of industrial SCADA/HMI interfaces such as graphical operator panels or control room visualization screens. Analysis of the designed HMI screens and quantitative and...
The article deals with methods of usability testing of industrial SCADA/HMI interfaces such as graphical operator panels or control room visualization screens. Analysis of the designed HMI screens and quantitative and qualitative testing methods are used. Usability is estimated by measuring the reaction times of the defined test tasks and by the Eye Tracking methods. The proposed method for testing and evaluating the industrial HMI is presented as a case study. The method allows for to improvement the quality of industrial HMI. Especially its usability, reliability, and efficiency.
In recent years, the manufacturing sector has undergone a significant transition from a paradigm of robotic autonomy to human-robot collaboration. This approach allows operators from different domains to rapidly adapt...
In recent years, the manufacturing sector has undergone a significant transition from a paradigm of robotic autonomy to human-robot collaboration. This approach allows operators from different domains to rapidly adapt to a new way of working and reduces redundant learning costs, while also enabling intuitive robot control. To further enhance this paradigm, integrating Mixed Reality (MR) technology has emerged as a promising approach to creating and working in a virtual workspace while having a safe environment for training. This work develops a framework, based on digital twin representation, to integrate the MR with real-life equipment and humans. This allows for the control of a collaborative robot in an environment with objects or humans perceived by the eye-in-hand visual sensor. The efficiency of the proposed framework is emphasized by a comparison of Unity simulations versus the real-time behavior of the collaborative robot.
Named Entity Recognition (NER) is a well-explored area from Information Retrieval and Natural Language Processing with an extensive research community. Despite that, few languages, such as English and German, are well...
详细信息
This paper presents a novel approach to Echo State Networks (ESNs) by integrating state-feedback with switching systems theory and the computational efficiency of Reservoir Computing architectures. We introduce an inn...
详细信息
ISBN:
(数字)9798350361933
ISBN:
(纸本)9798350361940
This paper presents a novel approach to Echo State Networks (ESNs) by integrating state-feedback with switching systems theory and the computational efficiency of Reservoir Computing architectures. We introduce an innovative architecture for ESNs, featuring a switching input weight and state-feedback gain, applicable to both linear and non-linear reservoirs. The stability of this architecture is rigorously analysed using the standard Lyapunov function construction method. Additionally, we explore the dynamical properties of a state-feedback ESN architecture used in the literature. The advantages of the proposed switching ESN is demonstrated using electrophysiological recordings in fruitfly photoreceptors.
暂无评论