Filters
total: 58
Search results for: cnn robustness detection uncertainty
-
An Analysis of Uncertainty and Robustness of Waterjet Machine Positioning Vision System
PublicationThe paper presents a new Automatic Waterjet Positioning Vision System (AWPVS) and investigates components of workpiece positioning accuracy. The main purpose of AWPVS is to precisely identify the position and rotation of a workpiece placed on a waterjet machine table. Two webcams form a basis for the system, and constitute its characteristics. The proposed algorithm comprises various image processing techniques to assure a required...
-
Robust Object Detection with Multi-input Multi-output Faster R-CNN
PublicationRecent years have seen impressive progress in visual recognition on many benchmarks, however, generalization to the out-of-distribution setting remains a significant challenge. A state-of-the-art method for robust visual recognition is model ensembling. However, recently it was shown that similarly competitive results could be achieved with a much smaller cost, by using multi-input multi-output architecture (MIMO). In this work,...
-
Robust Object Detection with Multi-input Multi-output Faster R-CNN
PublicationRecent years have seen impressive progress in visual recognition on many benchmarks, however, generalization to the out-of-distribution setting remains a significant challenge. A state-of-the-art method for robust visual recognition is model ensembling. However, recently it was shown that similarly competitive results could be achieved with a much smaller cost, by using multi-input multi-output architecture (MIMO). In this work,...
-
Toward Robust Pedestrian Detection With Data Augmentation
PublicationIn this article, the problem of creating a safe pedestrian detection model that can operate in the real world is tackled. While recent advances have led to significantly improved detection accuracy on various benchmarks, existing deep learning models are vulnerable to invisible to the human eye changes in the input image which raises concerns about its safety. A popular and simple technique for improving robustness is using data...
-
Robust Model Predictive Control for Autonomous Underwater Vehicle – Manipulator System with Fuzzy Compensator
PublicationThis paper proposes an improved Model Predictive Control (MPC) approach including a fuzzy compensator in order to track desired trajectories of autonomous Underwater Vehicle Manipulator Systems (UVMS). The tracking performance can be affected by robot dynamical model uncertainties and applied external disturbances. Nevertheless, the MPC as a known proficient nonlinear control approach should be improved by the uncertainty estimator...
-
Robust Model Predictive Control for Autonomous Underwater Vehicle–Manipulator System with Fuzzy Compensator
PublicationThis paper proposes an improved Model Predictive Control (MPC) approach including a fuzzy compensator in order totrack desired trajectories of autonomous Underwater Vehicle Manipulator Systems (UVMS). The tracking performancecan be affected by robot dynamical model uncertainties and applied external disturbances. Nevertheless, the MPCas a known proficient nonlinear control approach should be improved by the...
-
Robust and Efficient Machine Learning Algorithms for Visual Recognition
PublicationIn visual recognition, the task is to identify and localize all objects of interest in the input image. With the ubiquitous presence of visual data in modern days, the role of object recognition algorithms is becoming more significant than ever and ranges from autonomous driving to computer-aided diagnosis in medicine. Current models for visual recognition are dominated by models based on Convolutional Neural Networks (CNNs), which...
-
Semantic segmentation training using imperfect annotations and loss masking
PublicationOne of the most significant factors affecting supervised neural network training is the precision of the annotations. Also, in a case of expert group, the problem of inconsistent data annotations is an integral part of real-world supervised learning processes, well-known to researchers. One practical example is a weak ground truth delineation for medical image segmentation. In this paper, we have developed a new method of accurate...
-
An interval estimator for chlorine monitoring in drinking water distribution systems under uncertain system dynamics, inputs and chlorine concentration measurement errors
PublicationThe design of an interval observer for estimation of unmeasured state variables with application to drinking water distribution systems is described. In particular, the design process of such an observer is considered for estimation of the water quality described by the concentration of free chlorine. The interval observer is derived to produce the robust interval bounds on the estimated water quality state variables. The stability...
-
Closer Look at the Uncertainty Estimation in Semantic Segmentation under Distributional Shift
PublicationWhile recent computer vision algorithms achieve impressive performance on many benchmarks, they lack robustness - presented with an image from a different distribution, (e.g. weather or lighting conditions not considered during training), they may produce an erroneous prediction. Therefore, it is desired that such a model will be able to reliably predict its confidence measure. In this work, uncertainty estimation for the task...
-
Robustness in Compressed Neural Networks for Object Detection
PublicationModel compression techniques allow to significantly reduce the computational cost associated with data processing by deep neural networks with only a minor decrease in average accuracy. Simultaneously, reducing the model size may have a large effect on noisy cases or objects belonging to less frequent classes. It is a crucial problem from the perspective of the models' safety, especially for object detection in the autonomous driving...
-
A robust sliding mode observer for non-linear uncertain biochemical systems
PublicationA problem of state estimation for a certain class of non-linear uncertain systems has been addressed in this paper. In particular, a sliding mode observer has been derived to produce robust and stable estimates of the state variables. The stability and robustness of the proposed sliding mode observer have been investigated under parametric and unstructured uncertainty in the system dynamics. In order to ensure an unambiguous non-linear...
-
Multi-Criterial Design of Antennas with Tolerance Analysis Using Response-Feature Predictors
PublicationImperfect manufacturing is one of the factors affecting the performance of antenna systems. It is particularly important when design specifications are strict and leave a minimum leeway for a degradation caused by geometry or material parameter deviations from their nominal values. At the same time, conventional antenna design procedures routinely neglect to take the fabrication tolerances into account, which is mainly a result...
-
Hybrid SONIC: joint feedforward–feedback narrowband interference canceler
PublicationSONIC (self-optimizing narrowband interference canceler) is an acronym of a recently proposed active noise control algorithm with interesting adaptivity and robustness properties. SONIC is a purely feedback controller, capable of rejecting nonstationary sinusoidal disturbances (with time-varying amplitude and/or frequency) in the presence of plant (secondary path) uncertainty. We show that although SONIC can work reliably without...
-
Mispronunciation Detection in Non-Native (L2) English with Uncertainty Modeling
PublicationA common approach to the automatic detection of mispronunciation in language learning is to recognize the phonemes produced by a student and compare it to the expected pronunciation of a native speaker. This approach makes two simplifying assumptions: a) phonemes can be recognized from speech with high accuracy, b) there is a single correct way for a sentence to be pronounced. These assumptions do not always hold, which can result...
-
Interval estimator for chlorine monitoring in drinking water distribution systems under uncertain system dynamics, inputs and state measurement errors
PublicationThe design of interval observer for estimation of unmeasured state variables for application to drinking water distribution systems is described in this paper. In particular, it considers the design of such observer for estimation of water quality described by free chlorine concentration. An interval observer is derived to produce robust interval bounds on the estimated water quality state variables. The stability and robustness...
-
Tolerance Optimization of Antenna Structures by Means of Response Feature Surrogates
PublicationFabrication tolerances and other types of uncertainties, e.g., the lack of precise knowledge of material parameters, have detrimental effects on electrical and field performance of antenna systems. In the case of input characteristics these are particularly noticeable for narrow- and multi-band antennas where deviations of geometry parameters from their nominal values lead to frequency shifts of the operating frequency bands. Improving...
-
Computer-Aided Detection of Hypertensive Retinopathy Using Depth-Wise Separable CNN
PublicationHypertensive retinopathy (HR) is a retinal disorder, linked to high blood pressure. The incidence of HR-eye illness is directly related to the severity and duration of hypertension. It is critical to identify and analyze HR at an early stage to avoid blindness. There are presently only a few computer-aided systems (CADx) designed to recognize HR. Instead, those systems concentrated on collecting features from many retinopathy-related...
-
Deep CNN based decision support system for detection and assessing the stage of diabetic retinopathy
PublicationThe diabetic retinopathy is a disease caused by long-standing diabetes. Lack of effective treatment can lead to vision impairment and even irreversible blindness. The disease can be diagnosed by examining digital color fundus photographs of retina. In this paper we propose deep learning approach to automated diabetic retinopathy screening. Deep convolutional neural networks (CNN) - the most popular kind of deep learning algorithms...
-
Electrical and noise responses of carbon nanotube networks enhanced by UV light for nitrogen dioxide sensing
Open Research DataNetworks consisting of randomly oriented carbon nanotubes (CNN) were investigated toward nitrogen dioxide detection by means of electrical and low-frequency noise measurements. UV-activation of CNN layers improved gas sensitivity and reduced the limit of detection, especially by employing 275 nm-LED. This data set includes DC resistance measurements...