Aida I.G Raposo, Lius C.C Pires, Jose A.F. Moutinho, Pedro D. Silva, Ana R. Gouveia
{"title":"Development of a Thermographic Database with Images of the Vulva","authors":"Aida I.G Raposo, Lius C.C Pires, Jose A.F. Moutinho, Pedro D. Silva, Ana R. Gouveia","doi":"10.1145/3476779.3476785","DOIUrl":"https://doi.org/10.1145/3476779.3476785","url":null,"abstract":"This work aims to present a thermographic database of healthy vulva images and to explain the entire process of acquisition, processing, and analysis of the thermograms and other non-image information. We performed thermographic acquisitions of the vulva of 86 asymptomatic women and, after pre-processing and analyzing the thermograms, we obtained a total of 59 women with viable thermograms. To ensure we obtained at least one viable thermogram per women and to avoid loss of information due to human error, multiple acquisitions were made for each woman resulting in a total of 113 viable thermograms. All 113 thermograms were analyzed to guarantee that all the information obtained was included in the database. In this way, each thermogram was sectioned in 6 ROIs and the descriptive statistics were computed for each one. We identify the major difficulties of this process and present solutions for them.","PeriodicalId":203252,"journal":{"name":"4th International Conference on Biometric Engineering and Applications","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-05-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125571065","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Analysis of the Effect of Unified Diagnosis Framework for Automated Nuclear Cataract Grading Algorithm","authors":"Shenming Hu, Chaoqun Liu, Mary Adu, Wei He","doi":"10.1145/3476779.3476788","DOIUrl":"https://doi.org/10.1145/3476779.3476788","url":null,"abstract":"In this paper, we discuss the effectiveness and acceptability of unified diagnosis framework for automated nuclear cataract grading algorithm (UDFA) based on the mobile phone slit lamp. We obtain the effectiveness analysis data from June 2020 to December 2020 from Shenyang Eyerobo Company, three senior ophthalmologist classify 13816 eye images into three-way classification. The unified diagnosis framework for automated nuclear cataract grading algorithm was used to re-predict the results of eye images collected from September to December 2020 and the eye images retaken from the same eye under the same conditions to evaluate the consistency of the retest results of the algorithm. The sensitivity and specificity of the cataract deep learning algorithm were collected from 206 patients randomly selected from ophthalmic hospitals by 2 skilled operators using the mobile phone slit lamp to collect eye images. And we tested the algorithm in the north of Shenyang in Liaoning province for three months, to extract the rural doctors semi-structured interviews and its customers, to discuss their feelings after using. The mobile phone slit lamp is highly effective in screening cataract, and this new screening model has been accepted and recognized by users.","PeriodicalId":203252,"journal":{"name":"4th International Conference on Biometric Engineering and Applications","volume":"51 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-05-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122101798","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Gen Li, H. Cheng, Jie Hou, Dongfang Ding, Liuchuang Wei
{"title":"Construction of Cardiovascular System Experimental Simulation Platform and Research on Flow Change","authors":"Gen Li, H. Cheng, Jie Hou, Dongfang Ding, Liuchuang Wei","doi":"10.1145/3476779.3476789","DOIUrl":"https://doi.org/10.1145/3476779.3476789","url":null,"abstract":"The traditional Windkessel model cannot well explain how only a 1W multi-power heart overcomes various obstructions and viscous dissipation of the circulatory system, and smoothly transmits energy to the whole body. A closed-loop pressure system was built according to the cardiovascular structure. The experiments were carried out by changing the system pressure, the speed of the peristaltic pump and the stretch ratio of the experimental tube. The following conclusions were reached: 1. when the system pressure was 100mmHg, the speedwas70rad/min and the stretch ratiowas1.4, the maximum cumulative flow rate of 20min was 4991.7mL. 2. The average flow rate was positively correlated with the inner pipe pulse pressure (pulse pressure, PP), negatively correlated with the average pressure in the tube, and had no obvious relationship with the average pressure of inlet-outlet. 3. The inner pipe PP increased with the increase of circumferential elastic modulus of the experimental tube.","PeriodicalId":203252,"journal":{"name":"4th International Conference on Biometric Engineering and Applications","volume":"46 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-05-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128804280","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Mechanical Properties of Aortic Artery by Uniaxial Tensile Tests under Physiological Condition","authors":"Jifeng Dai, Jiangping Zhuang, Gen Li, H. Cheng","doi":"10.1145/3476779.3476796","DOIUrl":"https://doi.org/10.1145/3476779.3476796","url":null,"abstract":"As plenty of study have been done to investigate mechanical properties of arterial tissues from many aspects in order give a full description of the arterial tissues and to promote related clinical development, the mechanical behaviors of arterial tissues under physiological condition did not receive sufficient attention. In this study, we verified the nonlinearity, anisotropy and location dependent mechanical behaviors of porcine thoracic artery through planar uniaxial tests. We focused on the mechanical responses of the artery within the intra-vascular physiological blood pressure range of 60-120mmHg. Through the estimation of the strain and stress within the physiological range and the comparison of the anisotropy index, this study confirmed the anisotropic, location-dependent mechanical behaviors of the aortic tissues. The stiffness of the arterial tissues increases gradually from the proximal end to the distal end. Within the physiological range, the degree of nonlinearity of the arterial tissue is not obvious, although there are certain differences in the value of strain and stiffness of the arterial tissue under physiological condition. The stress range of the physiological range of different locations is relatively similar. We also found that within the range of physiological blood pressure, the degree of anisotropy of arterial tissue increases slightly from the proximal end to the distal end and increases gradually with the increase of blood pressure. Through the above research, this article is expected to increase the knowledge of the mechanical properties of arterial tissue under physiological conditions.","PeriodicalId":203252,"journal":{"name":"4th International Conference on Biometric Engineering and Applications","volume":"129 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-05-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124882880","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Huimin Li, Ying Zeng, Xiyu Song, Li Tong, Jun Shu, Bin Yan
{"title":"Sensitive Text Information Detection Based on Single-trial EEG Signals","authors":"Huimin Li, Ying Zeng, Xiyu Song, Li Tong, Jun Shu, Bin Yan","doi":"10.1145/3476779.3476782","DOIUrl":"https://doi.org/10.1145/3476779.3476782","url":null,"abstract":"P300 signals have been widely used to detect the sensitive event in Brain-Computer Interface (BCI) systems. Compared with image target detection, sensitive text information detection involves human brain's understanding of words and advanced semantic processing functions. The brain response induced by text-based sensitive information is still unclear. It is a challenge to expand the research from image target detection to sensitive text information detection. To solve this problem, a text information detection system based on rapid serial visual presentation (RSVP) paradigm was designed in this paper. The event-related potential responses caused by text-based sensitive information were estimated and identified by three classification methods (HDCA, sHDCA, EEGNet). The experimental results verified the feasibility of the experimental paradigm, and further showed that the proposed system can realize efficient information detection for massive texts.","PeriodicalId":203252,"journal":{"name":"4th International Conference on Biometric Engineering and Applications","volume":"46 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-05-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130341959","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Approach the Answer Step by Step–Application of Active Learning in Protein Subcellular Location Patterns","authors":"S. Deng","doi":"10.1145/3476779.3476786","DOIUrl":"https://doi.org/10.1145/3476779.3476786","url":null,"abstract":"When it comes to biological experiments, especially the experiments related to protein and drug binding, thorough experiments are not feasible because they will cost a lot of manpower and material resources [1]. Therefore, it has become a popular method to select a series of experiments to be carried out and effectively learns the model to predict the results of unfinished experiments, that is, active learning. Based on the existing experimental data, this paper discusses the feasibility of machine learning in biological experiments. Ordinary supervised learning and active learning are used to build prediction models, respectively. The difference between them is that active learning purposefully selects the \"most useful\" data for multiple rounds of learning, which is more in line with the needs of actual experiments. The result is that the accuracy of active learning is slightly higher than that of ordinary supervised learning when almost one fifth of the data of ordinary supervised learning is used.","PeriodicalId":203252,"journal":{"name":"4th International Conference on Biometric Engineering and Applications","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-05-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129781300","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"A Versatile Validation Framework for ERP and Oscillatory Brain Source Localization Using FieldTrip","authors":"Luca La Fisca, B. Gosselin","doi":"10.1145/3476779.3476781","DOIUrl":"https://doi.org/10.1145/3476779.3476781","url":null,"abstract":"The use of electroencephalography (EEG) continuously expanded during the last century leading this recording technique to be the standard in various domains. Considering its poor spatial resolution, many researchers have developed methods to reconstruct cortical source activations from scalp signals, but the lack of ground truth brain activity makes the reconstruction algorithms difficult to validate. To deal with this issue, simulated EEG data can be used to evaluate the reliability of the reconstructed sources. In the literature, benchmark frameworks are proposed to evaluate the reconstruction on fixed pseudo-EEG and other tools allow the user to generate custom data. However, to the best of our knowledge, none of the available pipelines proposes a uniform way to validate a reconstruction method from custom pseudo-data. We therefore present our versatile validation framework for EEG-based source localization. This new tool is an all-in-one validation pipeline aiming to evaluate source localization from pseudo-EEG data as close as possible to the experimental environment of the researcher. This paper presents the 5-step framework from the configuration to the evaluation and template data that can be used for benchmarking purposes. By using our uniform region-based evaluation method, researchers will be able to compare their reconstruction method on different configurations that fit their own experimental data. All the codes, template data and configuration description have been made available through https://github.com/numediart/ValidEEG.git.","PeriodicalId":203252,"journal":{"name":"4th International Conference on Biometric Engineering and Applications","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-05-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122236376","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Prediction of Drug Permeability to the Blood-Brain Barrier using Deep Learning","authors":"Abena Achiaa Atwereboannah, Wei-Ping Wu, Ebenezer Nanor","doi":"10.1145/3476779.3476797","DOIUrl":"https://doi.org/10.1145/3476779.3476797","url":null,"abstract":"In our quest to design new drugs, conventional means of designing drugs characterized by experiments is a time and resource demanding process. It involves exploring many molecular combinations, to find potential drugs to target indications. Machine Learning (ML) techniques upon their fantastic achievement in many application domains such as Computer vision and Natural Language Processing etc., are recently, being utilized in the research of drugs. With the surge in compound databases, ML and Deep Learning (DL) have shown great promise in various fields of drug discovery including pharmaceutics, biotechnology and physical chemistry. It is not incredible that these techniques are being incorporated in BBB studies. Predicting the permeability of drug compounds to the Blood-Brain Barrier (BBB) is indispensable for Central Nervous System (CNS) drug discovery, thus this work leverages two DL models in distinguishing between drugs that are BBB permeable and those that are not. The first architecture is a Fully-Connected Neural Network (FCNN) and the second is based on Convolutional Neural Network (CNN). Both algorithms were evaluated using two distinct CNS drug datasets. Our DL models generalize well, on both datasets and achieve competitive advantage over other ML and in silico techniques used in drug Blood–Brain Barrier Permeability (BBBP) prediction studies. The best performing model was the FCNN achieving AUROC of 99.5% on the first benchmark dataset.","PeriodicalId":203252,"journal":{"name":"4th International Conference on Biometric Engineering and Applications","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-05-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125390259","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"The Relationship between Pulse Wave Velocity and Heart-Period Variability","authors":"Rong-Chao Peng, Wen-Rong Yan","doi":"10.1145/3476779.3476783","DOIUrl":"https://doi.org/10.1145/3476779.3476783","url":null,"abstract":"The beat-to-beat heart-period variability (HPV) and pulse wave velocity (PWV) provide pivotal information on cardiac autonomic function that predicts arrhythmias and morbidity. However, their relationships have not been well understood. The present study is to investigate the relationship between heart period and PWV in beat-to-beat way and to determine the contribution of cold stimulus to their relationship. Experiments were conducted on 34 subjects in natural state and 55 subjects under cold stimulus. RR intervals (RRI) and PWV were calculated from simultaneously recorded electrocardiogram (ECG) and photoplethysmography (PPG) signals. Best correlation (r=-0.485) was obtained when RRI changes were delayed about 2.2 beats with respect to PWV changes, which confirmed the time-delay phenomenon between their variations. Overall, PWV was moderately negative correlated with RRI in their lower frequency components (fc<0.15Hz). Cold stimulus induced significant decreases in RRI and significant increases in PWV, and the variations of mean RRI and PWV (i.e., ΔHRV and ΔPWV) showed negative correlation (r=-0.48). Compared with natural state, cold stimulus mainly influenced their best delayed beats in the lower frequency components (fc< 0.15Hz). The results of this study suggest that RRI exhibit moderate correlation with PWV, and the effects of reactivity in response to cold stimulus on the relationship between RRI and PWV were mainly reflected in the low frequency components (fc< 0.15Hz), which might be helpful to understand the relationship among regulatory mechanisms of different cardiovascular risk factors.","PeriodicalId":203252,"journal":{"name":"4th International Conference on Biometric Engineering and Applications","volume":"516 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-05-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116222952","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"The Interaction of Ebola Virus with the Immune System Ebola and Immunity","authors":"J. Tian","doi":"10.1145/3476779.3476794","DOIUrl":"https://doi.org/10.1145/3476779.3476794","url":null,"abstract":"Ebola Virus Disease is one of the deadliest diseases known with a fatality rate of 90% caused by certain species. Ebola virus belongs to the family of Filoviridae viruses. Since its discovery in 1976, multiple outbreaks were reported around the world which had a great impact on global economy and public health system. Ebola virus is made of multiple components which can be targeted by different drugs as well as antibodies, one of them is its glycoprotein on the surface of the viral particle. The virus first replicates in the spleen and lymph nodes after entering the body and interferes with the host's type I Interferon response. Systemic inflammation is another characteristic feature of the disease. The incubation period of the disease is normally 5 to 7 days, and symptoms include fever, diarrhoea, myalgia, malaise, abdominal pain, nausea, and vomiting. As the disease progresses, haemorrhagic fever might also occur in the gastrointestinal tract. This paper aims to review recent advances on Ebola treatment and immune system by providing an overview of the latest findings. To this end, articles published in peer-reviewed journals in English between 1990 to 2019 were searched via publicly available databases such as PubMed, information were extracted and summarized. The results show that Ebola causes multi-organ failure, fulminant shock and eventually death. Recent advances on monoclonal antibodies can be used to treat the disease which are normally given as cocktails, and vaccines such as the recombinant vesicular stomatitis virus-vectored vaccine are also available. In conclusion, studying how Ebola virus works and developing effective treatment methods are very urgent and important.","PeriodicalId":203252,"journal":{"name":"4th International Conference on Biometric Engineering and Applications","volume":"57 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-05-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122489523","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}