scholarly journals A Preliminary Study on a Physical Model Oriented Learning Algorithm With Application to UAVs

2019 ◽  
Author(s):  
Minghui Zheng ◽  
Zhu Chen ◽  
Xiao Liang
Keyword(s):  
Physical Model ◽  
Learning Algorithm ◽  
Feedforward Control ◽  
Utilization Efficiency ◽  
Learning From Errors ◽  
Learning Capability ◽  
Learning Framework ◽  
Model Mapping ◽  
Preliminary Study ◽  
Efficient Learning

Abstract This paper provides a preliminary study for an efficient learning algorithm by reasoning the error from first principle physics to generate learning signals in near real time. Motivated by iterative learning control (ILC), this learning algorithm is applied to the feedforward control loop of the unmanned aerial vehicles (UAVs), enabling the learning from errors made by other UAVs with different dynamics or flying in different scenarios. This learning framework improves the data utilization efficiency and learning reliability via analytically incorporating the physical model mapping, and enhances the flexibility of the model-based methodology with equipping it with the self-learning capability. Numerical studies are performed to validate the proposed learning algorithm.

Dysarthria Profiles in Adults With Hereditary Ataxia

2019 ◽  
Vol 28 (2S) ◽  
pp. 915-924 ◽  
Author(s):  
Kristie A. Spencer ◽  
Mallory Dawson
Keyword(s):  
Rating Scales ◽  
Feedforward Control ◽  
Hereditary Ataxia ◽  
Severity Rating ◽  
Visual Analog Scales ◽  
Speech Characteristics ◽  
Ataxic Dysarthria ◽  
Preliminary Study

Purpose This preliminary study examined whether speech profiles exist for adults with hereditary ataxia based on 2 competing frameworks: a pattern of instability/inflexibility or a pattern of differential subsystem involvement. Method Four dysarthria experts rated the speech samples of 8 adults with dysarthria from hereditary ataxia using visual analog scales and presence/severity rating scales of speech characteristics. Speaking tasks included diadochokinetics, sustained phonation, and a monologue. Results Speech profiles aligned with the instability/inflexibility framework, with the pattern of instability being the most common. Speech profiles did not emerge for the majority of speakers using the differential subsystem framework. Conclusions The findings extend previous research on pure ataxic dysarthria and suggest a possible framework for understanding the speech heterogeneity associated with the ataxias. The predominance of the instability profile is consistent with the notion of impaired feedforward control in speakers with cerebellar disruption.

Stochastic Bayesian optimization for predicting borderline knock

2021 ◽  
pp. 146808742110652
Author(s):  
Jian Tang ◽  
Anuj Pal ◽  
Wen Dai ◽  
Chad Archer ◽  
James Yi ◽  
...  
Keyword(s):  
Fuel Economy ◽  
Learning Algorithm ◽  
Feedforward Control ◽  
Model Development ◽  
Kriging Model ◽  
Optimization Method ◽  
Surrogate Models ◽  
Bayesian Optimization ◽  
Control Parameters ◽  
Operation Conditions

Engine knock is an undesirable combustion that could damage the engine mechanically. On the other hand, it is often desired to operate the engine close to its borderline knock limit to optimize combustion efficiency. Traditionally, borderline knock limit is detected by sweeping tests of related control parameters for the worst knock, which is expensive and time consuming, and also, the detected borderline knock limit is often used as a feedforward control without considering its stochastic characteristics without compensating current engine operational condition and type of fuel used. In this paper, stochastic Bayesian optimization method is used to obtain a tradeoff between stochastic knock intensity and fuel economy. The log-nominal distribution of knock intensity signal is converted to Gaussian one using a proposed map to satisfy the assumption for Kriging model development. Both deterministic and stochastic Kriging surrogate models are developed based on test data using the Bayesian iterative optimization process. This study focuses on optimizing two competing objectives, knock intensity and indicated specific fuel consumption using two control parameters: spark and intake valve timings. Test results at two different operation conditions show that the proposed learning algorithm not only reduces required time and cost for predicting knock borderline but also provides control parameters, based on trained surrogate models and the corresponding Pareto front, with the best fuel economy possible.

scholarly journals Learning Tractable Word Alignment Models with Complex Constraints

2010 ◽  
Vol 36 (3) ◽  
pp. 481-504 ◽  
Author(s):  
João V. Graça ◽  
Kuzman Ganchev ◽  
Ben Taskar
Keyword(s):  
Probabilistic Models ◽  
Learning Algorithm ◽  
Word Alignment ◽  
Word Level ◽  
Word Alignments ◽  
Symmetry Constraints ◽  
Critical Resource ◽  
Complex Constraints ◽  
Bilingual Text ◽  
Efficient Learning

Word-level alignment of bilingual text is a critical resource for a growing variety of tasks. Probabilistic models for word alignment present a fundamental trade-off between richness of captured constraints and correlations versus efficiency and tractability of inference. In this article, we use the Posterior Regularization framework (Graça, Ganchev, and Taskar 2007) to incorporate complex constraints into probabilistic models during learning without changing the efficiency of the underlying model. We focus on the simple and tractable hidden Markov model, and present an efficient learning algorithm for incorporating approximate bijectivity and symmetry constraints. Models estimated with these constraints produce a significant boost in performance as measured by both precision and recall of manually annotated alignments for six language pairs. We also report experiments on two different tasks where word alignments are required: phrase-based machine translation and syntax transfer, and show promising improvements over standard methods.

Improving Active Output Capacity of Large-Scale Wind Farm by Installation STATCOM

2012 ◽  
Vol 588-589 ◽  
pp. 574-577 ◽  
Author(s):  
Yan Juan Wu ◽  
Lin Chuan Li
Keyword(s):  
Control Strategy ◽  
Large Scale ◽  
Wind Farm ◽  
Transient Stability ◽  
Reactive Power ◽  
Feedforward Control ◽  
Wind Farms ◽  
Active Power ◽  
Utilization Efficiency ◽  
Grid Voltage

Some faults will result wind turbine generators off-grid due to low grid voltage , furthermore, large-scale wind farms tripping can result in severe system oscillation and aggravate system transient instability . In view of this, static compensator (STATCOM) is installed in the grid containing large-scale wind farm. A voltage feedforward control strategy is proposed to adjust the reactive power of STATCOM compensation and ensure that the grid voltage is quickly restored to a safe range. The mathematical model of the doubly-fed induction wind generator (DFIG) is proposed. The control strategy of DFIG uses PI control for rotor angular velocity and active power. 4-machine system simulation results show that the STATCOM reactive power compensation significantly improve output active power of large-scale wind farm satisfying transient stability, reduce the probability of the tripping, and improve the utilization efficiency of wind farms.

FKPIndexNet: An efficient learning framework for finger-knuckle-print database indexing to boost identification

2021 ◽  
pp. 108028
Author(s):  
Geetika Arora ◽  
Avantika Singh ◽  
Aditya Nigam ◽  
Hari Mohan Pandey ◽  
Kamlesh Tiwari
Keyword(s):  
Learning Framework ◽  
Database Indexing ◽  
Efficient Learning

scholarly journals Contextual-Bandit Based Personalized Recommendation with Time-Varying User Interests

2020 ◽  
Vol 34 (04) ◽  
pp. 6518-6525
Author(s):  
Xiao Xu ◽  
Fang Dong ◽  
Yanghua Li ◽  
Shaojian He ◽  
Xin Li
Keyword(s):  
Learning Algorithm ◽  
General Setting ◽  
Personalized Recommendation ◽  
Time Varying ◽  
Bandit Problem ◽  
User Interests ◽  
Specific Preference ◽  
Coefficient Vector ◽  
Real World Datasets ◽  
Efficient Learning

A contextual bandit problem is studied in a highly non-stationary environment, which is ubiquitous in various recommender systems due to the time-varying interests of users. Two models with disjoint and hybrid payoffs are considered to characterize the phenomenon that users' preferences towards different items vary differently over time. In the disjoint payoff model, the reward of playing an arm is determined by an arm-specific preference vector, which is piecewise-stationary with asynchronous and distinct changes across different arms. An efficient learning algorithm that is adaptive to abrupt reward changes is proposed and theoretical regret analysis is provided to show that a sublinear scaling of regret in the time length T is achieved. The algorithm is further extended to a more general setting with hybrid payoffs where the reward of playing an arm is determined by both an arm-specific preference vector and a joint coefficient vector shared by all arms. Empirical experiments are conducted on real-world datasets to verify the advantages of the proposed learning algorithms against baseline ones in both settings.

An SVM-Based Ensemble Approach for Intrusion Detection

2019 ◽  
Vol 14 (1) ◽  
pp. 66-84 ◽  
Author(s):  
Santosh Kumar Sahu ◽  
Akanksha Katiyar ◽  
Kanchan Mala Kumari ◽  
Govind Kumar ◽  
Durga Prasad Mohapatra
Keyword(s):  
Support Vector Machine ◽  
Intrusion Detection ◽  
Learning Algorithm ◽  
Majority Voting ◽  
Support Vector ◽  
Detection Model ◽  
Ensemble Approach ◽  
Efficient Learning

The objective of this article is to develop an intrusion detection model aimed at distinguishing attacks in the network. The aim of building IDS relies on upon preprocessing of intrusion data, choosing most relevant features and in the plan of an efficient learning algorithm that properly groups the normal and malicious examples. In this experiment, the detection model uses an ensemble approach of supervised (SVM) and unsupervised (K-Means) to detect the patterns. This technique first divides the data and forms two clusters as per K-Means and labels the clusters using the Support Vector Machine (SVM). The parameters of K-Means and SVM are tuned and optimized using an intrusion dataset. The SVM provides up to 88%, and K-Means provides up to 83% accuracy individually. However, the ensemble of K-Means and SVM provides more than 99% on three benchmarked datasets in less time. The SVM only classifies three instances of each cluster randomly and labels them as per a majority voting approach. The proposed approach outperforms compared to earlier ensemble approaches on intrusion datasets.

Sign in / Sign up

Export Citation Format

Share Document