2019 International Conference on Intelligent Informatics and Biomedical Sciences (ICIIBMS)最新文献

{"title":"Improved Edge Detection Model Based on HED","authors":"Wenju Li, Maoxian He","doi":"10.1109/ICIIBMS46890.2019.8991484","DOIUrl":"https://doi.org/10.1109/ICIIBMS46890.2019.8991484","url":null,"abstract":"Influenced by the HED network structure, how to further solve the image multi-scale multi-level representation problem and optimize the detection of the overall image. We propose an end-to-end network structure. While enhancing the robustness of backbone network, the BN layer is used to solve the problem of network gradient dispersion, the attention mechanism is added to strengthen the role of deep supervision and final fusion module. The network can learn related semantic features autonomously, obtain richer image information, and solve the problem that HED cannot fully extract features, and high-level and low-level information are simply fused together. Considering the modification on the basis of the HED network structure, the BN layer and the SE structure are added, and the manner of downsampling is modified. The experimental results show that the edge effect from the BSDS300 data set is good, and the running speed is better than the HED model.","PeriodicalId":444797,"journal":{"name":"2019 International Conference on Intelligent Informatics and Biomedical Sciences (ICIIBMS)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126350846","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 New DC-DC Converter for Server Power Supply with Fast Dynamic Response","authors":"Jian-Kun Lu, Ziyu Zhao","doi":"10.1109/ICIIBMS46890.2019.8991489","DOIUrl":"https://doi.org/10.1109/ICIIBMS46890.2019.8991489","url":null,"abstract":"The DC-DC converter for server power supply requires wide range of the input voltage and load variation, and it ought to have long hold-up time when power failure, therefore, this paper takes LLC Resonant Full-bridge Circuit as the base topology to design DC-DC converter. Firstly, using First Harmonic Approximation (FHA) to calculate the resonant parameters of the converter, and using Extension Describing Function (EDF) to establish small-signal model. Secondly, applying the Fractional Order PID (FOPID) controller and using the Particle Swarm Optimization (PSO) algorithm to tune FOPID parameters for the optimization control to solve the problem that the dynamic response ability and the ripple of the output voltage of the LLC resonant full bridge converter cannot be sufficient for the server power supply, meanwhile, the integer order PID controller is designed in the same method for comparison. Finally the simulation verified that using FOPID controller the converter has less ripple of the output voltage and it could supply with faster dynamic response, and the speed might close to 2-4 times comparing with PID controller, it indiciates that the system is more stable and it could satisfy the most requirements of the server power supply.","PeriodicalId":444797,"journal":{"name":"2019 International Conference on Intelligent Informatics and Biomedical Sciences (ICIIBMS)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131007510","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":"Medical Information Storage Model Based on Block Chain","authors":"Wang Zi-chen, Wu Xiaoyu, Y. Wan-jun, Li Jia-lan, Zhao Huai-lin, Cang Nai-meng","doi":"10.1109/ICIIBMS46890.2019.8991479","DOIUrl":"https://doi.org/10.1109/ICIIBMS46890.2019.8991479","url":null,"abstract":"How to effectively control data access rights in the medical field and securely share data between hospitals is an important challenge in the standardization of medical information in China. This paper proposes a model of data access and secure sharing by using the decentralization, tamper resistance and traceability of blockchain. The system utilizes attribute-based encryption technology to ensure the authenticity of information and solve the problems of information asymmetry in the traditional medical field, difficulty in information inquiry, difficulty in positioning of responsible persons, and inability to trace information.","PeriodicalId":444797,"journal":{"name":"2019 International Conference on Intelligent Informatics and Biomedical Sciences (ICIIBMS)","volume":"62 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133083717","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":"Filtering for Systems with Sensor Nonlinearities and Data Losses: An Interval Type-2 Fuzzy-Model-Based Method","authors":"Xiuying Li, Xianghua Ma, Fei Wang, Lei Zhang","doi":"10.1109/ICIIBMS46890.2019.8991461","DOIUrl":"https://doi.org/10.1109/ICIIBMS46890.2019.8991461","url":null,"abstract":"This paper focuses on designing H∞ filter for networked nonlinear systems subject to sensor saturations and packet dropouts. To capture the system uncertainties effectively, an interval type-2 (IT2) fuzzy model approach is applied. When the sensor outputs are lost during the transmission through the network links, the redundant channels are adopted to reduce the negative effect of packet dropouts. An IT2 filter is designed, where the membership functions and the number of fuzzy rules need not as the same as those of the plant, such that the filtering error system is guaranteed to be stochastically stable with prescribed H∞ performance. Finally, an example is utilized to illustrate the effectiveness of the algorithm.","PeriodicalId":444797,"journal":{"name":"2019 International Conference on Intelligent Informatics and Biomedical Sciences (ICIIBMS)","volume":"52 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123798287","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":"Identification of markers of acute inflammatory process in the pulmonary tuberculosis","authors":"Diljara S. Esmedljaeva, A. Lavrova, V. Belik, E. Postnikov","doi":"10.1109/ICIIBMS46890.2019.8991449","DOIUrl":"https://doi.org/10.1109/ICIIBMS46890.2019.8991449","url":null,"abstract":"Tuberculosis remains, according to the WHO report, one of the global problems in the world, especially in the form caused by drug-resistant mycobacteria. The identification of special biochemical markers allowing to assess the necessity of surgery or therapy prolongation remains a challenge. We consider promising markers – metalloproteinases – analyzing statistics of data obtained from patients with pulmonary tuberculosis forced by different strains of Mycobacterium tuberculosis. The discussed results could be used for further development of a precise biochemical data-based diagnostic and prognostic tool.","PeriodicalId":444797,"journal":{"name":"2019 International Conference on Intelligent Informatics and Biomedical Sciences (ICIIBMS)","volume":"78 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116009802","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":"An OCT-enable Minimally-invasive Neurosurgical Guide for in-situ Brain Monitoring","authors":"Tsung-Yi Tsai, De Yi Chiou","doi":"10.1109/ICIIBMS46890.2019.8991485","DOIUrl":"https://doi.org/10.1109/ICIIBMS46890.2019.8991485","url":null,"abstract":"As many advanced countries, including Taiwan, are beginning to enter the aging society, so the aging diseases such as Parkinson's Disease (PD) will be an inevitable issue in the 21st century. In order to provide a better quality of treatment, the Deep Brain Simulation (DBS) procedure is suggested to be adopted for the neurological treatment. For DBS, the key to the success of the treatment is the DBS stimulation electrode can act at right position, in other words, the electrode must be accurately implanted in the target area. At present, the surgical navigation for DBS relies on the pre-operative CT/MRI and intra-operative MER (microelectrode recording); however, some limitations are found in these methods. Therefore, As the result, an minimally-invasive guiding tool providing real-time localization information is required for assisting physician modifying the path for the safe and precise implantation of electrodes. To meet the unmet needs as mentioned previously, an innovative optical coherence tomography-guided DBS (OCTgDBS) system with a high slender ratio (0.7 mm outer diameter and 30 cm length) of forward-imaging needle is developed without any contrast agent. A 1323 nm swept source laser with 20 kHz A-scan rate and bandwidth of 127 nm is used. The OCTgDBS system performance such as axial resolution is about 6 µm and SNR is up to 81.75 dB. We successfully distinguished the tissue structure of ex vivo swine brain and found that white matter has stronger backscatters and steeper attenuation rate than gray matter. The results demonstrate that the OCTgDBS system is an alternative neurosurgical guiding approach for in-situ brain monitoring.","PeriodicalId":444797,"journal":{"name":"2019 International Conference on Intelligent Informatics and Biomedical Sciences (ICIIBMS)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130119266","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":"Effect of different musculoskeletal model scaling methods on muscle force prediction for patients with cerebral palsy and equinus gait","authors":"Yunru Ma, Yan Yu, Shuyun Jiang, N. Wilson, K. Mithraratne, Yanxin Zhang","doi":"10.1109/ICIIBMS46890.2019.8991443","DOIUrl":"https://doi.org/10.1109/ICIIBMS46890.2019.8991443","url":null,"abstract":"Patient-specific musculoskeletal models are always acquired by scaling the generic ones. Different scaling methods can influence joint kinematics and affect musculotendon kinematics. The latter is an input of EMG-driven modelling and static optimization for muscle force estimation. For children with cerebral palsy (CP) and equinus gait, the ankle kinematics is a key indicator for gait classification that can be affected by scaling methods. Effects of scaling methods on muscle force estimation for such a paediatric group is not investigated yet. This study aimed at evaluating the modelling performance with two scaling methods (scaling only by static marker positions and by both static marker positions and joint angles pre-calculated from a static pose). In this study, three children with CP and equinus gait underwent standard gait analysis. Inverse kinematics, inverse dynamics, muscle analysis, static optimization and EMG-assist modelling were conducted to obtain the tibialis anterior (TA), lateral gastrocnemius (LG), medial gastrocnemius (MG) and soleus (SL) muscle forces. The coefficient of multiple correlation (CMC) and root mean squared error (RMSE) values were calculated to compare the difference between the two scaling methods. Triceps surae forces calculated by static optimization showed very good to the excellent similarity between two scaling methods. Conversely, TA force estimation seemed to be more sensitive to the scaling method chosen. For the EMG-assist modelling, LG and MG muscle forces showed a good agreement between two scaling models in contrast to SL and TA. In conclusion, TA muscle force estimation is susceptible to the scaling method irrespective of the muscle modelling approach. A possible reason may be due to different definitions of ankle joint axes and degrees of freedom. In EMG-driven modelling, SL’s mono-articular role and its optimized muscle excitation may be the reason for its sensitivity to scaling methods. Future studies should not only involve more participants and EMG channels but also apply medical imaging and other clinical assessment methods to validate the effect of scaling methods on the performance of muscle modelling approaches.","PeriodicalId":444797,"journal":{"name":"2019 International Conference on Intelligent Informatics and Biomedical Sciences (ICIIBMS)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130379312","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":"Defect detection of mobile phone screen based on improved difference image method","authors":"Jianguo Zhang, Ying Li, Chunmei Zuo, Mingxing Xing","doi":"10.1109/ICIIBMS46890.2019.8991460","DOIUrl":"https://doi.org/10.1109/ICIIBMS46890.2019.8991460","url":null,"abstract":"The defect inspection with machine vision plays an important role in the quality control of mobile phone screen manufacturing. An improved difference image method is proposed to detect the defects of mobile phone screen. Considering the problem of misalignment of mobile phone screen image, PatMax algorithm and image correction technology based on affine transform are adopted to realize pixel alignment between template image and testing image. With the intention of eliminating noise effects and protecting the edge information of the test image, a image filtering is performed by 3×3 median filtering. Based on the above image preprocessing results, the defect-free image is used as the template image and the fuzzy processing is carried out, the differential operational between the testing image and the template image is performed to obtain the residual image, and the improved Otsu dual threshold method is used to achieve defect judgment on residual images. The experimental results show that the approach proposed in this study has achieved high efficiency and accuracy.","PeriodicalId":444797,"journal":{"name":"2019 International Conference on Intelligent Informatics and Biomedical Sciences (ICIIBMS)","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123724058","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":"Predicting potential drug abusers using machine learning techniques","authors":"Zhaoying Qiao, Tianrui Chai, Qinjing Zhang, Xinyi Zhou, Zhuoling Chu","doi":"10.1109/ICIIBMS46890.2019.8991550","DOIUrl":"https://doi.org/10.1109/ICIIBMS46890.2019.8991550","url":null,"abstract":"Drug abuse is a noteworthy public health problem in the world. Recently, machine learning has become a favorable tool for classification problem. In this paper, we selected three machine learning algorithms (random forest (RF), Extreme Gradient Boosting (XGBoost) and Light Gradient Boosting Machine (LightGBM) ) to predict potential abuse individuals of methamphetamine and amyl nitrite, two kinds of central stimulants, as well as users’ last consumption time based on personality traits and demographic information. Compared with k-NearestNeighbor, a widely-used classification algorithm, RF, XGBoost and LightGBM have superior performance, with LightGBM being the most efficient one in predicting potential user and estimating usage time. The results of feature importance indicate neuroticism is the most important predictor of drug abuse risk.","PeriodicalId":444797,"journal":{"name":"2019 International Conference on Intelligent Informatics and Biomedical Sciences (ICIIBMS)","volume":"65 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121645126","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}