Pubfacts - Scientific Publication Data
  • Categories
  • |
  • Journals
  • |
  • Authors
  • Login
  • Categories
  • Journals

Search Our Scientific Publications & Authors

Publications
  • Publications
  • Authors
find publications by category +
Translate page:

Large-scale recognition of natural landmarks with deep learning based on biomimetic sonar echoes.

Authors:
Liujun Zhang Rolf Müller

Bioinspir Biomim 2022 02 11;17(2). Epub 2022 Feb 11.

Virginia Tech, Mechanical Engineering, Blacksburg, VA 24060, United States of America.

The ability to identify natural landmarks on a regional scale could contribute to the navigation skills of echolocating bats and also advance the quest for autonomy in natural environments with man-made systems. However, recognizing natural landmarks based on biosonar echoes has to deal with the unpredictable nature of echoes that are typically superpositions of contributions from many different reflectors with unknown properties. The results presented here show that a deep neural network (ResNet50) was able to classify ten different field sites and 20 different tracks (two at each site) distributed over an area about 40 km in diameter. Based on spectrogram representations of single echoes, classification accuracies up to 99.6% for different sites and 94.7% for different tracks have been achieved. Classification performance was found to depend on the used pulse component (constant-frequency-CF vs frequency-modulated-FM) and the trade-off between time and frequency resolution in the spectrogram representations of the echoes. For the former, classification performance increased monotonically with better time resolution. For the latter, classification performance peaked at an intermediate trade-off point between time and frequency resolution indicating that both dimensions contained relevant information. Future work will be needed to further characterize the quality of the spatial information contained in the echoes, e.g. in terms of spatial resolution and potential ambiguities.

Download full-text PDF

Source
http://dx.doi.org/10.1088/1748-3190/ac4c94DOI Listing
February 2022

Publication Analysis

Top Keywords

classification performance
12
natural landmarks
12
frequency resolution
8
echoes classification
8
time frequency
8
spectrogram representations
8
echoes
6
performance peaked
4
site distributed
4
large-scale recognition
4
tracks site
4
resnet50 classify
4
sites tracks
4
field sites
4
ten field
4
peaked intermediate
4
classify ten
4
intermediate trade-off
4
neural network
4
network resnet50
4

Keyword Occurance

Similar Publications

Increasing the confidence of F-Florbetaben PET interpretations: Machine learning quantitative approximation.

Authors:
Ana María García Vicente María Jesús Tello Galán Francisco José Pena Pardo Mariano Amo-Salas Beatriz Mondejar Marín Santiago Navarro Muñoz Ignacio Rueda Medina Víctor Manuel Poblete García Carlos Marsal Alonso Ángel Soriano Castrejón

Rev Esp Med Nucl Imagen Mol (Engl Ed) 2022 May-Jun;41(3):153-163. Epub 2021 Apr 21.

Nuclear Medicine Department, University General Hospital, Ciudad Real, Spain.

Aim: To assess the added value of semiquantitative parameters on the visual assessment and to study the patterns of F-Florbetaben brain deposition.

Materials And Methods: Retrospective analysis of multicenter study performed in patients with mild cognitive impairment or dementia of uncertain origin. F-Florbetaben PET scans were visually interpreted by two experienced observers, analyzing target regions in order to calculate the interobserver agreement. Read More

View Article and Full-Text PDF
April 2021
Similar Publications

Application of the New Preoperative Frailty Risk Score in Elderly Patients Undergoing Emergency Surgery.

Authors:
Sang-Wook Lee Keon-Sik Kim Sung-Wook Park Jaewon Kim Jeong-Hyun Choi Sangho Lee Kyoung-Woon Joung In-Cheol Choi

Gerontology 2022 May 16:1-9. Epub 2022 May 16.

Department of Anesthesiology and Pain Medicine, Asan Medical Center, University of Ulsan College of Medicine, Seoul, Republic of Korea.

Background: Predicting preoperative frailty risk in emergency surgery is difficult with limited information because preoperative evaluation is not commonly performed properly. A recent study attempted to predict preoperative frailty risk using only diagnostic and surgical codes that can be extracted from the electronic medical records system.

Objective: This study aimed to validate whether the prediction model of preoperative frailty risk presented in the previous study is well applied to other medical hospitals' data. Read More

View Article and Full-Text PDF
May 2022
Similar Publications

Renal Interstitial Inflammation Predicts Nephropathy Progression in IgA Nephropathy: A Two-Center Cohort Study.

Authors:
Bin Zhu Wen-Hua Liu Yi Lin Qiang Li Dong-Rong Yu Fei Jiang Xuan-Li Tang Yuan-Yuan Du Jia-Zhen Yin Xian-Fa Li Yong-Zhong Zhong Wen-Rong Wang Yue Sun Mei-Juan Zhang Yuan-Cheng Gao Chen-Yi Yuan Cai-Feng Zhu Xiao-Xia Cheng

Am J Nephrol 2022 May 16:1-15. Epub 2022 May 16.

Department of Nephrology, Hangzhou Hospital of Chinese Medicine (Guangxing Hospital), Affiliated to Zhejiang University of Chinese Medicine, Hangzhou, China.

Introduction: Renal interstitial inflammation often presents in immunoglobulin A nephropathy (IgAN), but its predictive role in kidney disease progression remains controversial.

Methods: This retrospective two-center cohort study included 1,420 adult IgAN patients between January 2003 and May 2018 followed for a median of approximately 7 years at two Chinese hospitals. The predictor was renal interstitial inflammation within the total cortical interstitium (none/mild [0-25%], moderate [26-50%], or severe [>50%]). Read More

View Article and Full-Text PDF
May 2022
Similar Publications

A simple assessment model based on phase angle for malnutrition and prognosis in hospitalized cancer patients.

Authors:
Xiaoling Zhang Wenqi Zhao Yunyi Du Jialei Zhang Ying Zhang Weiling Li Wenqing Hu Liang Zong Yaqin Liu Haifeng Qin Jun Zhao

Clin Nutr 2022 Apr 26;41(6):1320-1327. Epub 2022 Apr 26.

Department of Oncology, Changzhi People's Hospital Affiliated to Shanxi Medical University, Shanxi Province, 046000, China. Electronic address:

Background & Aims: Malnutrition in cancer patients is a common but under-diagnosed condition that has negative effects on clinical outcomes. The development of an easy and reliable malnutrition assessment tool is thus critical for identification and nutritional support. We aimed to develop a phase angle (PA)-based prediction model of malnutrition and evaluate it in patient prognosis. Read More

View Article and Full-Text PDF
April 2022
Similar Publications

Insomnia disorder diagnosed by resting-state fMRI-based SVM classifier.

Authors:
Dongmei He Dongmei Ren Zhiwei Guo Binghu Jiang

Sleep Med 2022 Apr 30;95:126-129. Epub 2022 Apr 30.

Institute of Brain Function, Nanchong Central Hospital, The Second Clinical Medical College, North Sichuan Medical College, Nanchong, 637000, Sichuan, China. Electronic address:

Background: The main classification systems of sleep disorders are based on the subjective self-reported criteria. Objective measures are essential to characterize the nocturnal sleep disturbance, identify daytime impairment, and determine the course of these symptoms. The aim of this study was to establish a resting-state fMRI-based support vector machine (SVM) classifier to diagnose insomnia disorder. Read More

View Article and Full-Text PDF
April 2022
Similar Publications
}
© 2022 PubFacts.
  • About PubFacts
  • Privacy Policy
  • Sitemap