USE OF NEURAL NETWORKS IN ADAPTIVE ELECTRIC CAR CONTROL

To overcome the lack of information about the parameters of the driving cycle of the electric car, neural networks are used, which provide adaptive control that allows you to adapt. electric car to external operating conditions, as well as to compensate for inaccuracies in mathematical models. Use of iterative optimization of parameters allows to adjust optimum work of power plant of the electric car (PEC) in the course of its movement. This method allows you to use a single approach to study different processes, regardless of the parametric features of electric vehicles. To accelerate adaptation, the neurocontroller and neural network model are trained using a reference control model, which is either an optimal strategy or a strategy based on logical rules of choice, obtained by methodical programming for a given driving cycle. Based on the results of the research, an adaptation algorithm is proposed. The expressions given in the article allow to carry out adaptation of the power plant on the basis of hybrid to the current driving cycle on the basis of the concept of training of the neuro-fuzzy controller with reinforcement. The expressions given in the article allow to carry out adaptation of the power plant on the basis of hybrid to the current driving cycle on the basis of the concept of training of the neuro-fuzzy controller with reinforcement. The purpose of training the neuro-fuzzy controller is the formation of such control effects of the power plant, which would reduce the quadratic value of the assessment of the quality of management.

A Semi-Supervised Transfer Learning with Dynamic Associate Domain Adaptation for Human Activity Recognition Using WiFi Signals

Human activity recognition without equipment plays a vital role in smart home applications, freeing humans from the shackles of wearable devices. In this paper, by using the channel state information (CSI) of the WiFi signal, semi-supervised transfer learning with dynamic associate domain adaptation is proposed for human activity recognition. In order to improve the CSI quality and denoising of CSI, we carried out missing packet filling, burst noise removal, background estimation, feature extraction, feature enhancement, and data augmentation in the data pre-processing stage. This paper considers the problem of environment-independent human activity recognition, also known as domain adaptation. The pre-trained model is trained from the source domain by collecting a complete labeled dataset of all of the CSI of human activity patterns. Then, the pre-trained model is transferred to the target environment through the semi-supervised transfer learning stage. Therefore, when humans move to different target domains, a partial labeled dataset of the target domain is required for fine-tuning. In this paper, we propose a dynamic associate domain adaptation called DADA. By modifying the existing associate domain adaptation algorithm, the target domain can provide a dynamic ratio of labeled dataset/unlabeled dataset, while the existing associate domain adaptation algorithm only allows target domains with the unlabeled dataset. The advantage of DADA is that it provides a dynamic strategy to eliminate different effects on different environments. In addition, we further designed an attention-based DenseNet model, or AD, as our training network, which is modified by an existing DenseNet by adding the attention function. The solution we proposed was simplified to DADA-AD throughout the paper. The experimental results show that for domain adaptation in different domains, the accuracy of human activity recognition of the DADA-AD scheme is 97.4%. It also shows that DADA-AD has advantages over existing semi-supervised learning schemes.

The analysis of modern tools of positioning of the working mechanism road construction ma-chines on building

The task of positioning the working mechanisms CRM at this time is not enough. As a result of the analysis the purpose of research is set, namely: to increase of functioning efficiency mechanisms CRM with working environment using mathematical models and adaptation algorithm in a limited time decision. Such methods of analysis include fractal analysis, neural network method, fuzzy set method, geostatistical data analysis. The element base of positioning systems and benefits of implementation are substantiated. The use of a GPS intensifier makes it possible to predict the work of actuators CRM in real time. The result of the research is algorithm of positioning the working mechanisms CRM: determination of the location of the base CRM in a 3-dimensional coordinate system; filtering measurements; predicting the position of the working mechanism (the algorithm for choosing a solution for the state of the monitored object is based on both the probability of obtaining certain results and their usefulness). The originality lies in the fact that the using modern information and software tools allows to describe the trajectory in the coordinate system of the base machine in accordance with the point measurement, and describe the relationship between changed coordinates, which makes it possible to model and predict the workflow. Proposals for the use of software in positioning systems, which provides adaptive optimization and advantages of introduction of the newest technologies of intellectualization of work processes.

CycleStyleGAN-Based Knowledge Transfer for a Machining Digital Twin

Digitalisation of manufacturing is a crucial component of the Industry 4.0 transformation. The digital twin is an important tool for enabling real-time digital access to precise information about physical systems and for supporting process optimisation via the translation of the associated big data into actionable insights. Although a variety of frameworks and conceptual models addressing the requirements and advantages of digital twins has been suggested in the academic literature, their implementation has received less attention. The work presented in this paper aims to make a proposition that considers the novel challenges introduced for data analysis in the presence of heterogeneous and dynamic cyber-physical systems in Industry 4.0. The proposed approach defines a digital twin simulation tool that captures the dynamics of a machining vibration signal from a source model and adapts them to a given target environment. This constitutes a flexible approach to knowledge extraction from the existing manufacturing simulation models, as information from both physics-based and data-driven solutions can be elicited this way. Therefore, an opportunity to reuse the costly established systems is made available to the manufacturing businesses, and the paper presents a process optimisation framework for such use case. The proposed approach is implemented as a domain adaptation algorithm based on the generative adversarial network model. The novel CycleStyleGAN architecture extends the CycleGAN model with a style-based signal encoding. The implemented model is validated in an experimental scenario that aims to replicate a real-world manufacturing knowledge transfer problem. The experiment shows that the transferred information enables the reduction of the required target domain data by one order of magnitude.

Experimental Study on the Performance of Rate Adaptation Algorithm in IEEE 802.11g Networks

<p>IEEE 802.11 technology provides a low-cost wireless networking solution. In the last few years, we have seen that the demand for high-bandwidth wireless local area networks increases rapidly, due to the proliferation of mobile devices such as laptops, smart phones and tablet PCs. This has driven the widespread deployment of IEEE 802.11 wireless networks to provide Internet access. However, wireless networks present their own unique problems. Wireless channel is extremely variable and can be affected by a number of different factors, such as collisions, multipath fading and signal attenuation. As such, rate adaptation algorithm is a key component of IEEE 802.11 standard which is used to vary the transmission data rate to match the wireless channel conditions, in order to achieve the best possible performance. Rate adaptation algorithm studies and evaluations are always hot research topics. However, despite its popularity, little work has been done on evaluating the performance of rate adaptation algorithms by comparing the throughput of the algorithm with the throughput of the fixed rates. This thesis presents an experimental study that compares the performance ofMikroTik rate adaptation algorithm andMinstrel rate adaptation algorithm against fixed rates in an IEEE 802.11g network. MikroTik and Minstrel rate adaptation algorithm are most commonly used algorithm around the world. All experiments are conducted in a real world environment in this thesis. In a real world environment, wireless channel conditions are not tightly being controlled, and it is extremely vulnerable to interference of surrounding environment. The dynamic changes of wireless channel conditions have a considerable effect on the performance of rate adaptation algorithms. The main challenge of evaluating a rate adaptation algorithm in a real world environment is getting different experiment behaviours from the same experiment. Experiment results may indicate many different behaviours which due to the leak of wireless environment controlling. Having a final conclusion from those experiment results can be a challenge task. In order to perform a comprehensive rate adaptation algorithm evaluation. All experiments run 20 times for 60 seconds. The average result and stand deviation is calculated. We also design and implement an automation experiment controlling program to help us maintain that each run of experiment is following exactly the same procedures. In MikroTik rate adaptation algorithm evaluation, the results show in many cases that fixed rate outperforms rate adaptation. Our findings raise questions regarding the suitability of the adopted rate adaptation algorithm in typical indoor environments. Furthermore, our study indicates that it is not wise to simply ignore fixed rate. A fine selection of a fixed rate could be made to achieve desired performance. The result ofMinstrel rate adaptation evaluation show that whilst Minstrel performs reasonably well in static wireless channel conditions, in some cases the algorithm has difficulty selecting the optimal data rate in the presence of dynamic channel conditions. In addition, Minstrel performs well when the channel condition improves frombad quality to good quality. However, Minstrel has trouble selecting the optimal rate when the channel condition deteriorates from good quality to bad quality. By comparing the experimental results between the performance of rate adaptation algorithms and the performance of fixed data rate against different factors, the experiment results directly pointed out the weakness of these two rate adaptation algorithms. Our findings from both experiments provide useful information on the design of rate adaptation algorithms.</p>

Experimental Study on the Performance of Rate Adaptation Algorithm in IEEE 802.11g Networks

<p>IEEE 802.11 technology provides a low-cost wireless networking solution. In the last few years, we have seen that the demand for high-bandwidth wireless local area networks increases rapidly, due to the proliferation of mobile devices such as laptops, smart phones and tablet PCs. This has driven the widespread deployment of IEEE 802.11 wireless networks to provide Internet access. However, wireless networks present their own unique problems. Wireless channel is extremely variable and can be affected by a number of different factors, such as collisions, multipath fading and signal attenuation. As such, rate adaptation algorithm is a key component of IEEE 802.11 standard which is used to vary the transmission data rate to match the wireless channel conditions, in order to achieve the best possible performance. Rate adaptation algorithm studies and evaluations are always hot research topics. However, despite its popularity, little work has been done on evaluating the performance of rate adaptation algorithms by comparing the throughput of the algorithm with the throughput of the fixed rates. This thesis presents an experimental study that compares the performance ofMikroTik rate adaptation algorithm andMinstrel rate adaptation algorithm against fixed rates in an IEEE 802.11g network. MikroTik and Minstrel rate adaptation algorithm are most commonly used algorithm around the world. All experiments are conducted in a real world environment in this thesis. In a real world environment, wireless channel conditions are not tightly being controlled, and it is extremely vulnerable to interference of surrounding environment. The dynamic changes of wireless channel conditions have a considerable effect on the performance of rate adaptation algorithms. The main challenge of evaluating a rate adaptation algorithm in a real world environment is getting different experiment behaviours from the same experiment. Experiment results may indicate many different behaviours which due to the leak of wireless environment controlling. Having a final conclusion from those experiment results can be a challenge task. In order to perform a comprehensive rate adaptation algorithm evaluation. All experiments run 20 times for 60 seconds. The average result and stand deviation is calculated. We also design and implement an automation experiment controlling program to help us maintain that each run of experiment is following exactly the same procedures. In MikroTik rate adaptation algorithm evaluation, the results show in many cases that fixed rate outperforms rate adaptation. Our findings raise questions regarding the suitability of the adopted rate adaptation algorithm in typical indoor environments. Furthermore, our study indicates that it is not wise to simply ignore fixed rate. A fine selection of a fixed rate could be made to achieve desired performance. The result ofMinstrel rate adaptation evaluation show that whilst Minstrel performs reasonably well in static wireless channel conditions, in some cases the algorithm has difficulty selecting the optimal data rate in the presence of dynamic channel conditions. In addition, Minstrel performs well when the channel condition improves frombad quality to good quality. However, Minstrel has trouble selecting the optimal rate when the channel condition deteriorates from good quality to bad quality. By comparing the experimental results between the performance of rate adaptation algorithms and the performance of fixed data rate against different factors, the experiment results directly pointed out the weakness of these two rate adaptation algorithms. Our findings from both experiments provide useful information on the design of rate adaptation algorithms.</p>

Cross-Layer Adaptation with Safety-Assured Proactive Task Job Skipping

During the operation of many real-time safety-critical systems, there are often strong needs for adapting to a dynamic environment or evolving mission objectives, e.g., increasing sampling and control frequencies of some functions to improve their performance under certain situations. However, a system's ability to adapt is often limited by tight resource constraints and rigid periodic execution requirements. In this work, we present a cross-layer approach to improve system adaptability by allowing proactive skipping of task executions, so that the resources can be either saved directly or re-allocated to other tasks for their performance improvement. Our approach includes three novel elements: (1) formal methods for deriving the feasible skipping choices of control tasks with safety guarantees at the functional layer, (2) a schedulability analysis method for assessing system feasibility at the architectural layer under allowed task job skippings, and (3) a runtime adaptation algorithm that efficiently explores job skipping choices and task priorities for meeting system adaptation requirements while ensuring system safety and timing correctness. Experiments demonstrate the effectiveness of our approach in meeting system adaptation needs.

A Framework for Self-Supervised Federated Domain Adaptation

Unsupervised federated domain adaptation uses the knowledge from several distributed unlabelled source domains to complete the learning on the unlabelled target domain. Some of the existing methods have limited effectiveness and involve frequent communication. This paper proposes a framework to solve the distributed multi-source domain adaptation problem, referred as self-supervised federated domain adaptation (SFDA). Specifically, a multi-domain model generalization balance (MDMGB) is proposed to aggregate the models from multiple source domains in each round of communication. A weighted strategy based on centroid similarity is also designed for SFDA. SFDA conducts self-supervised training on the target domain to tackle domain shift. Compared with the classical federated adversarial domain adaptation algorithm, SFDA is not only strong in communication cost and privacy protection but also improves in the accuracy of the model.

Bias-invariant RNA-sequencing metadata annotation

Background Recent technological advances have resulted in an unprecedented increase in publicly available biomedical data, yet the reuse of the data is often precluded by experimental bias and a lack of annotation depth and consistency. Missing annotations makes it impossible for researchers to find datasets specific to their needs. Findings Here, we investigate RNA-sequencing metadata prediction based on gene expression values. We present a deep-learning–based domain adaptation algorithm for the automatic annotation of RNA-sequencing metadata. We show, in multiple experiments, that our model is better at integrating heterogeneous training data compared with existing linear regression–based approaches, resulting in improved tissue type classification. By using a model architecture similar to Siamese networks, the algorithm can learn biases from datasets with few samples. Conclusion Using our novel domain adaptation approach, we achieved metadata annotation accuracies up to 15.7% better than a previously published method. Using the best model, we provide a list of &gt;10,000 novel tissue and sex label annotations for 8,495 unique SRA samples. Our approach has the potential to revive idle datasets by automated annotation making them more searchable.