scholarly journals Classification of Inter-Floor Noise Type/Position Via Convolutional Neural Network-Based Supervised Learning

2019 ◽  
Vol 9 (18) ◽  
pp. 3735 ◽  
Author(s):  
Hwiyong Choi ◽  
Haesang Yang ◽  
Seungjun Lee ◽  
Woojae Seong
Keyword(s):  
University Campus ◽  
Deep Convolutional Neural Networks ◽  
Test Dataset ◽  
Noise Type ◽  
National University ◽  
Human Hearing ◽  
Seoul National University ◽  
Type Classification ◽  
Campus Building

Inter-floor noise, i.e., noise transmitted from one floor to another floor through walls or ceilings in an apartment building or an office of a multi-layered structure, causes serious social problems in South Korea. Notably, inaccurate identification of the noise type and position by human hearing intensifies the conflicts between residents of apartment buildings. In this study, we propose a robust approach using deep convolutional neural networks (CNNs) to learn and identify the type and position of inter-floor noise. Using a single mobile device, we collected nearly 2000 inter-floor noise events that contain 5 types of inter-floor noises generated at 9 different positions on three floors in a Seoul National University campus building. Based on pre-trained CNN models designed and evaluated separately for type and position classification, we achieved type and position classification accuracy of 99.5% and 95.3%, respectively in validation datasets. In addition, the robustness of noise type classification with the model was checked against a new test dataset. This new dataset was generated in the building and contains 2 types of inter-floor noises at 10 new positions. The approximate positions of inter-floor noises in the new dataset with respect to the learned positions are presented.

Questionnaire-based diagnosis of benign paroxysmal positional vertigo

Neurology ◽  
2019 ◽  
Vol 94 (9) ◽  
pp. e942-e949 ◽  
Author(s):  
Hyo-Jung Kim ◽  
Jeong-Mi Song ◽  
Liqun Zhong ◽  
Xu Yang ◽  
Ji-Soo Kim
Keyword(s):  
Confidence Interval ◽  
Gold Standard ◽  
Benign Paroxysmal Positional Vertigo ◽  
Class Iii ◽  
Positional Vertigo ◽  
National University ◽  
Seoul National University ◽  
Sensitivity Specificity ◽  
Paroxysmal Positional Vertigo

ObjectivesTo develop a simple questionnaire for self-diagnosis of benign paroxysmal positional vertigo (BPPV).MethodsWe developed a questionnaire that consisted of 6 questions, the first 3 to diagnose BPPV and the next 3 to determine the involved canal and type of BPPV. From 2016 to 2017, 578 patients with dizziness completed the questionnaire before the positional tests, a gold standard for diagnosis of BPPV, at the Dizziness Clinic of Seoul National University Bundang Hospital.ResultsOf the 578 patients, 200 were screened to have BPPV and 378 were screened to have dizziness/vertigo due to disorders other than BPPV. Of the 200 patients with a questionnaire-based diagnosis of BPPV, 160 (80%) were confirmed to have BPPV with positional tests. Of the 378 patients with a questionnaire-based diagnosis of non-BPPV, 24 (6.3%) were found to have BPPV with positional tests. Thus, the sensitivity, specificity, and precision of the questionnaires for the diagnosis of BPPV were 87.0%, 89.8%, and 80.0% (121 of 161, 95% confidence interval 74.5%–85.5%). Of the 200 patients with a questionnaire-based diagnosis of BPPV, 30 failed to respond to the questions 4 through 6 to determine the involved canal and type of BPPV. The questionnaire and positional tests showed the same results for the subtype and affected side of BPPV in 121 patients (121 of 170, 71.2%).ConclusionThe accuracy of questionnaire-based diagnosis of BPPV is acceptable.Classification of evidenceThis study provides Class III evidence that, in patients with dizziness, a questionnaire can diagnose BPPV with a sensitivity of 87.0% and a specificity of 89.8%.

scholarly journals Ensemble of Deep Convolutional Neural Networks for Classification of Early Barrett’s Neoplasia Using Volumetric Laser Endomicroscopy

2019 ◽  
Vol 9 (11) ◽  
pp. 2183 ◽  
Author(s):  
Roger Fonollà ◽  
Thom Scheeve ◽  
Maarten R. Struyvenberg ◽  
Wouter L. Curvers ◽  
Albert J. de Groof ◽  
...  
Keyword(s):  
Neural Networks ◽  
Convolutional Neural Networks ◽  
Characteristic Curve ◽  
Patient Treatment ◽  
Deep Convolutional Neural Networks ◽  
Test Dataset ◽  
Novel Technology ◽  
Multi Center Study ◽  
Work Done

Barrett’s esopaghagus (BE) is a known precursor of esophageal adenocarcinoma (EAC). Patients with BE undergo regular surveillance to early detect stages of EAC. Volumetric laser endomicroscopy (VLE) is a novel technology incorporating a second-generation form of optical coherence tomography and is capable of imaging the inner tissue layers of the esophagus over a 6 cm length scan. However, interpretation of full VLE scans is still a challenge for human observers. In this work, we train an ensemble of deep convolutional neural networks to detect neoplasia in 45 BE patients, using a dataset of images acquired with VLE in a multi-center study. We achieve an area under the receiver operating characteristic curve (AUC) of 0.96 on the unseen test dataset and we compare our results with previous work done with VLE analysis, where only AUC of 0.90 was achieved via cross-validation on 18 BE patients. Our method for detecting neoplasia in BE patients facilitates future advances on patient treatment and provides clinicians with new assisting solutions to process and better understand VLE data.

IgH Gene Rearrangements Are Strongly Associated with Hyperdiploidy Variant Multiple Myeloma in Korea: A Contradiction to the Pathogenetic Pathway of IgH Tranlocations in Non Hyperdiploidy Variant.

Blood ◽  
2005 ◽  
Vol 106 (11) ◽  
pp. 5084-5084
Author(s):  
Hee Won Moon ◽  
Tae Young Kim ◽  
Seong- Ho Kang ◽  
Hyun-Sook Chi ◽  
Eul Zu Seo ◽  
...  
Keyword(s):  
Multiple Myeloma ◽  
Medical Center ◽  
Cytogenetic Study ◽  
University Hospital ◽  
Korean Patients ◽  
National University ◽  
Asan Medical ◽  
Seoul National University

Abstract Recent studies proposed the classification of multiple myeloma (MM) by the pathways involved in the early pathogenesis; nonhyperdiploid variants with a high incidence of IgH translocations and hyperdiploid variants associated with no IgH translocation. Most studies applied cytogenetic study or flow cytometry to define the ploidy. In this study, we combined the cytogenetic results and fluorescent in situ hybridization results to define the ploidy and investigated IgH tranlocation and 13q deletion in relation to the ploidy level on Korean patients with MM. A total of 135 cases diagnosed as MM between 1997 and 2003 from Seoul National University Hospital and the Asan Medical center were enrolled in this study. Conventional cytogenetic studies and FISH studies with different probes specific for the regions containing the genes or chromosomes (RB1, D13S319, D13S25, IgH/FGFR3, IgH/BCL2, IGH dual color, break apart rearrangement probe, IgH/CCND1, 1q, p53, p16, MLL, CEP 7, 11, 12) were performed. Of 135 patients with MM, 62 (45.9%) patients had hyperdiploid karyotype by cytogenetics and FISH. IgH translocations were observed in 37.4% of Korean patients with MM and were more frequent (54.7%) in hyperdiploid variants than in nonhyperdiploid variants (17.4%). Incidence of deletion 13q was 34.7% and also more frequent in hyperdiploid variants (54.2%) than in nonhyperdiploid variants (16.1%). In conclusion, IgH translocations and 13q deletions were not associated with nonhyperdiploid MM and appeared more frequently in hyperdiploid variant in Korean patients with MM.

High-dose diazepam controls severe dyskinesia in Anti-NMDA receptor encephalitis

2020 ◽  
pp. 10.1212/CPJ.0000000000001001
Author(s):  
Hye-Rim Shin ◽  
Yoonhyuk Jang ◽  
Yong-Won Shin ◽  
Kon Chu ◽  
Sang Kun Lee ◽  
...  
Keyword(s):  
Nmda Receptor ◽  
University Hospital ◽  
High Dose ◽  
Serious Adverse Events ◽  
Nmda Receptor Encephalitis ◽  
Nmdar Encephalitis ◽  
National University ◽  
Seoul National University ◽  
Severe Dyskinesia

ObjectiveSince there is no standard treatment to control dyskinesia in anti-NMDA receptor (NMDAR) encephalitis, we analyzed therapeutic efficacy of high-dose diazepam in dyskinesia associated with NMDAR encephalitis.MethodsWe reviewed NMDAR encephalitis patients with dyskinesia, who were admitted to Seoul National University Hospital between November 2012 and July 2018. High-dose diazepam was administered orally or via a nasogastric tube, 3–6 times a day. We assessed the treatment effect by comparing dyskinesia severity on the first day when the diazepam treatment reached the highest dose, with after 1 week of highest dose of diazepam treatment.ResultsAmong 68 NMDAR encephalitis patients during study period, 33 patients were treated with enteral diazepam (ranging from 6 mg to 180 mg) to control dyskinesia, along with immunotherapy. The severity of dyskinesia improved from average grade 2.4 ± 0.6 to 1.1 ± 0.7, after 1 week of the highest dose of diazepam (mean severity change −1.4 ± 0.6, 95% confidence interval −1.2 to −1.6; p < 0.001). No patients had serious adverse events except mild sedation.ConclusionsDyskinesia in NMDAR encephalitis improved after treatment with enteral diazepam without significant side effects. This study suggests enteral diazepam could be a treatment option for control dyskinesia in NMDAR encephalitis.Classification of evidenceThis study provides Class IV evidence that for patients with dyskinesias associated with NMDAR encephalitis, enteral diazepam is effective and safe in dyskinesia control.

scholarly journals Ensemble of Deep Convolutional Neural Networks for Classification of Early Barrett's Neoplasia Using Volumetric Laser Endomicroscopy

2019 ◽  
Author(s):  
Roger Fonollà ◽  
Thom Scheeve ◽  
Maarten R. Struyvenberg ◽  
Wouter L. Curvers ◽  
Albert J. de Groof ◽  
...  
Keyword(s):  
Neural Networks ◽  
Convolutional Neural Networks ◽  
Multicenter Study ◽  
Patient Treatment ◽  
Deep Convolutional Neural Networks ◽  
Test Dataset ◽  
Novel Technology ◽  
Vle Data ◽  
Work Done

Barrett's esopaghagus (BE) is a known precursor of esophageal adenocarcinoma (EAC). Patients with BE undergo regular surveillance to early detect stages of EAC. Volumetric laser endomicroscopy (VLE) is a novel technology capable of imaging the inner tissue layers of the esophagus over a 6-cm length scan. However, interpretation of full VLE scans is still a challenge for human observers. In this work, we train an ensemble of deep convolutional neural networks to detect neoplasia in BE patients, using a dataset of images acquired with VLE in a multicenter study. We achieve values of AUC=$0.96$ on the unseen test dataset and we compare our results with previous work done with VLE analysis. Our method for detecting neoplasia in BE patients facilitates future advances on patient treatment and provides clinicians with new assisting solutions to process and better understand VLE data.

CNN-based Classification of Degraded Images

2020 ◽  
Vol 2020 (10) ◽  
pp. 28-1-28-7 ◽  
Author(s):  
Kazuki Endo ◽  
Masayuki Tanaka ◽  
Masatoshi Okutomi
Keyword(s):  
Neural Networks ◽  
Image Restoration ◽  
Image Classification ◽  
Convolutional Neural Networks ◽  
Deep Convolutional Neural Networks ◽  
Alternative Approach ◽  
Degraded Image ◽  
Degraded Images ◽  
Straightforward Approach

Classification of degraded images is very important in practice because images are usually degraded by compression, noise, blurring, etc. Nevertheless, most of the research in image classification only focuses on clean images without any degradation. Some papers have already proposed deep convolutional neural networks composed of an image restoration network and a classification network to classify degraded images. This paper proposes an alternative approach in which we use a degraded image and an additional degradation parameter for classification. The proposed classification network has two inputs which are the degraded image and the degradation parameter. The estimation network of degradation parameters is also incorporated if degradation parameters of degraded images are unknown. The experimental results showed that the proposed method outperforms a straightforward approach where the classification network is trained with degraded images only.

Sign in / Sign up

Export Citation Format

Share Document