Testing Accuracy and Agreement among Multiple Versions of Automated Bat Call Classification Software

2021 ◽  
Author(s):  
Katy R. Goodwin ◽  
Erin H. Gillam
Keyword(s):  
Call Classification ◽  
Testing Accuracy

Developing an inkjet printer IV: printer mechanism control for best print quality

2020 ◽  
Vol 2020 (15) ◽  
pp. 349-1-349-9
Author(s):  
Daulet Kenzhebalin ◽  
Baekdu Choi ◽  
Sige Hu ◽  
Yin Wang ◽  
Davi He ◽  
...  
Keyword(s):  
Motor Control ◽  
Constant Velocity ◽  
Control Problems ◽  
Print Quality ◽  
Control Parameters ◽  
Test Page ◽  
Mechanism Control ◽  
Testing Accuracy ◽  
Inkjet Printer

Inkjet printer motor control consists of moving the printhead in the scan direction and in the process direction. Both movements have different objectives. Scan direction movement needs to have constant velocity and process direction movement needs to have accurate movement. In this paper, we discuss a method for controlling the velocity of the printhead and how to tune the motor control parameters. We also design six test pages for testing accuracy of the printhead movement and cartridge properties. For each test page, we discuss expected prints, common printer control problems that could alter the print quality, and how to identify them.

scholarly journals Fuzzy Evaluation Model of Process Improvement Capability with Costs Consideration

2021 ◽  
Vol 11 (10) ◽  
pp. 4344
Author(s):  
Kuen-Suan Chen ◽  
Shui-Chuan Chen ◽  
Ting-Hsin Hsu ◽  
Min-Yi Lin ◽  
Chih-Feng Wu
Keyword(s):  
Process Improvement ◽  
Quality Evaluation ◽  
Evaluation Model ◽  
Fuzzy Evaluation ◽  
Sampling Errors ◽  
Capability Index ◽  
Testing Method ◽  
Improvement Potential ◽  
Testing Accuracy

The Taguchi capability index, which reflects the expected loss and the yield of a process, is a useful index for evaluating the quality of a process. Several scholars have proposed a process improvement capability index based on the expected value of the Taguchi loss function as well as the corresponding cost of process improvement. There have been a number of studies using the Taguchi capability index to develop suppliers’ process quality evaluation models, whereas models for evaluating suppliers’ process improvement potential have been relatively lacking. Thus, this study applies the process improvement capability index to develop an evaluation model of the supplier’s process improvement capability, which can be provided to the industry for application. Besides, owing to the current need to respond quickly, coupled with cost considerations and the limits of technical capabilities, the sample size for sampling testing is usually not large. Consequently, the evaluation model of the process improvement capability developed in this study adopts a fuzzy testing method based on the confidence interval. This method reduces the risk of misjudgment due to sampling errors and improves the testing accuracy because it can incorporate experts and their accumulated experiences.

scholarly journals Adaptive frequency scaled wavelet packet decomposition for frog call classification

2016 ◽  
Vol 32 ◽  
pp. 134-144 ◽  
Author(s):  
Jie Xie ◽  
Michael Towsey ◽  
Jinglan Zhang ◽  
Paul Roe
Keyword(s):  
Wavelet Packet ◽  
Wavelet Packet Decomposition ◽  
Call Classification

A Design of End Effector for Measuring Robot Orientation Accuracy and Repeatability

2011 ◽  
Vol 137 ◽  
pp. 382-386 ◽  
Author(s):  
Xiao Ping Zhang ◽  
Wan Chun Yan ◽  
Wei Zhu ◽  
Tao Wen
Keyword(s):  
Cost Effective ◽  
Structure Parameters ◽  
End Effector ◽  
Testing Tool ◽  
Manufacturing Errors ◽  
Testing Accuracy ◽  
Accuracy And Repeatability

This paper represents the design of a robot end effector which is supposed to be a tool of measuring the orientation accuracy and repeatability. The motivations and ideas of this testing tool are stated, firstly. Then, its structure parameters are specified and the testing accuracy is computed by mean of analyzing the manufacturing errors and structure stiffness which are measured and simulated by Carl Zeiss CMM and Abaqus, respectively. Moreover, the orientation accuracy and repeatability of Kunshan No.1 and KUKA L16 are tested in terms of ISO 9283 standard using this testing tool and API Tracker3. Finally, the results are analyzed and compared which show that the design of this testing end effector is competent with a high cost-effective ratio.

TAMI-22. SEGMENTATION OF DISTINCT TUMOR HALLMARKS OF GLIOBLASTOMA ON DIGITAL HISTOPATHOLOGY USING A HIERARCHICAL DEEP LEARNING APPROACH

2021 ◽  
Vol 23 (Supplement_6) ◽  
pp. vi202-vi203
Author(s):  
Alvaro Sandino ◽  
Ruchika Verma ◽  
Yijiang Chen ◽  
David Becerra ◽  
Eduardo Romero ◽  
...  
Keyword(s):  
Deep Learning ◽  
Blood Vessels ◽  
Network Architecture ◽  
Automatic Segmentation ◽  
Area Under The Curve ◽  
Primary Treatment ◽  
Microvascular Proliferation ◽  
Vascular Proliferation ◽  
Testing Accuracy ◽  
Future Work

Abstract PURPOSE Glioblastoma is a highly heterogeneous brain tumor. Primary treatment for glioblastoma involves maximally-safe surgical resection. After surgery, resected tissue slides are visually analyzed by neuro-pathologists to identify distinct histological hallmarks characterizing glioblastoma including high cellularity, necrosis, and vascular proliferation. In this work, we present a hierarchical deep learning-based strategy to automatically segment distinct Glioblastoma niches including necrosis, cellular tumor, and hyperplastic blood vessels, on digitized histopathology slides. METHODS We employed the IvyGap cohort for which Hematoxylin and eosin (H&E) slides (digitized at 20X magnification) from n=41 glioblastoma patients were available. Additionally, expert-driven segmentations of cellular tumor, necrosis, and hyperplastic blood vessels (along with other histological attributes) were made available. We randomly employed n=120 slides from 29 patients for training, n=38 slides from 6 cases for validation, and n=30 slides from 6 patients to feed our deep learning model based on Residual Network architecture (ResNet-50). ~2,000 patches of 224x224 pixels were sampled for every slide. Our hierarchical model included first segmenting necrosis from non-necrotic (i.e. cellular tumor) regions, and then from the regions segmented as non-necrotic, identifying hyperplastic blood-vessels from the rest of the cellular tumor. RESULTS Our model achieved a training accuracy of 94%, and a testing accuracy of 88% with an area under the curve (AUC) of 92% in distinguishing necrosis from non-necrotic (i.e. cellular tumor) regions. Similarly, we obtained a training accuracy of 78%, and a testing accuracy of 87% (with an AUC of 94%) in identifying hyperplastic blood vessels from the rest of the cellular tumor. CONCLUSION We developed a reliable hierarchical segmentation model for automatic segmentation of necrotic, cellular tumor, and hyperplastic blood vessels on digitized H&E-stained Glioblastoma tissue images. Future work will involve extension of our model for segmentation of pseudopalisading patterns and microvascular proliferation.

Deep Learning-Based Knowledge Extraction From Diseased and Healthy Edible Plant Leaves

2021 ◽  
Vol 12 (2) ◽  
pp. 67-81
Author(s):  
Udit Jindal ◽  
Sheifali Gupta
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Plant Disease ◽  
Disease Detection ◽  
Edible Plant ◽  
Research Article ◽  
Segmented Images ◽  
Significant Area ◽  
Testing Accuracy ◽  
Disease Present

Agriculture contributes majorly to all nations' economies, but crop diseases are now becoming a very big issue that has to be resolving immediately. Because of this, crop/plant disease detection becomes a very significant area to work. However, a huge number of studies have been done for automatic disease detection using machine learning, but less work has been done using deep learning with efficient results. The research article presents a convolution neural network for plant disease detection by using open access ‘PlantVillage' dataset for three versions that are colored, grayscale, and segmented images. The dataset consists of 54,305 images and is being used to train a model that will be able to detect disease present in edible plants. The proposed neural network achieved the testing accuracy of 99.27%, 98.04%, and 99.14% for colored, grayscale, and segmented images, respectively. The work also presents better precision and recall rates on colored image datasets.

scholarly journals Evaluation of point-of-care glucose testing accuracy using locally-smoothed median absolute difference curves

2008 ◽  
Vol 389 (1-2) ◽  
pp. 31-39 ◽  
Author(s):  
Gerald J. Kost ◽  
Nam K. Tran ◽  
Victor J. Abad ◽  
Richard F. Louie
Keyword(s):  
Point Of Care ◽  
Absolute Difference ◽  
Glucose Testing ◽  
Testing Accuracy ◽  
Median Absolute Difference
Sign in / Sign up

Export Citation Format

Share Document