Pub Date : 2018-11-01DOI: 10.1109/ICBME.2018.8703561
Elnaz Mohammadi, M. Orooji
The white blood cell (WBC) segmentation and classification is a challenging task, due to the different shapes of the nucleus, cytoplasm and the number of lobes. The purpose of this paper is to provide a method for fast and accurate segmentation of leukocyte in smear images by a convolutional neural network (CNN) model and Gaussian Mixture Model (GMM) approach. The first step is the usage of white balance and selfdual multiscale morphological toggle (SMMT) to increase the contrast between the nucleus and cytoplasm. To segment, each WBC and corresponded nucleus and cytoplasm regions, a CNN model with 10 layers and GMM are used, respectively. In the postprocessing step, removing undesired objects by size, closing, and filling morphological operations are applied to each segment. The proposed method is validated on peripheral smear blood images in Cellavision dataset. This dataset contains 27 images which include different types of normal leukocytes. In order to evaluate the proposed method, the Dice coefficient, Jaccard and F1-score are used. The experimental results demonstrate the high accuracy for segmentation results of different types of WBC.
{"title":"An Unsupervised and Supervised Combined Approach for White Blood Cells Segmentation","authors":"Elnaz Mohammadi, M. Orooji","doi":"10.1109/ICBME.2018.8703561","DOIUrl":"https://doi.org/10.1109/ICBME.2018.8703561","url":null,"abstract":"The white blood cell (WBC) segmentation and classification is a challenging task, due to the different shapes of the nucleus, cytoplasm and the number of lobes. The purpose of this paper is to provide a method for fast and accurate segmentation of leukocyte in smear images by a convolutional neural network (CNN) model and Gaussian Mixture Model (GMM) approach. The first step is the usage of white balance and selfdual multiscale morphological toggle (SMMT) to increase the contrast between the nucleus and cytoplasm. To segment, each WBC and corresponded nucleus and cytoplasm regions, a CNN model with 10 layers and GMM are used, respectively. In the postprocessing step, removing undesired objects by size, closing, and filling morphological operations are applied to each segment. The proposed method is validated on peripheral smear blood images in Cellavision dataset. This dataset contains 27 images which include different types of normal leukocytes. In order to evaluate the proposed method, the Dice coefficient, Jaccard and F1-score are used. The experimental results demonstrate the high accuracy for segmentation results of different types of WBC.","PeriodicalId":338286,"journal":{"name":"2018 25th National and 3rd International Iranian Conference on Biomedical Engineering (ICBME)","volume":"56 3","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132738301","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}
Pub Date : 2018-11-01DOI: 10.1109/ICBME.2018.8703548
Shayan Jalilpour, S. H. Sardouie
In this paper a novel auditory BCI paradigm based on P300 responses which are generated by auditory stimuli is proposed. In the proposed protocol, stimuli are different from each other and there is no need to repeat each single stimulus. Instead of that, a 30-word list containing different words as stimuli is played for the subject. Each letter is repeated in four different words of the list. Ensemble support vector machine and regularized linear discriminant analysis classifiers are used to evaluate the proposed protocol. The result of the offline classification of the P300 responses of one subject shows we can achieve accuracy and ITR of 88% and 3.51 bit/min for three iterations of the list (twelve repetitions of a letter).
{"title":"A Novel Auditory BCI for Spelling Persian Words","authors":"Shayan Jalilpour, S. H. Sardouie","doi":"10.1109/ICBME.2018.8703548","DOIUrl":"https://doi.org/10.1109/ICBME.2018.8703548","url":null,"abstract":"In this paper a novel auditory BCI paradigm based on P300 responses which are generated by auditory stimuli is proposed. In the proposed protocol, stimuli are different from each other and there is no need to repeat each single stimulus. Instead of that, a 30-word list containing different words as stimuli is played for the subject. Each letter is repeated in four different words of the list. Ensemble support vector machine and regularized linear discriminant analysis classifiers are used to evaluate the proposed protocol. The result of the offline classification of the P300 responses of one subject shows we can achieve accuracy and ITR of 88% and 3.51 bit/min for three iterations of the list (twelve repetitions of a letter).","PeriodicalId":338286,"journal":{"name":"2018 25th National and 3rd International Iranian Conference on Biomedical Engineering (ICBME)","volume":"106 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130441475","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}
Pub Date : 2018-11-01DOI: 10.1109/ICBME.2018.8703599
Mohammad Jazlaeiyan, Sanaz Seyedin, S. A. Motamedi
Human visual system can robustly and simply recognize complex objects in cluttered natural scenes. So far, numerous computational models have been developed to mimic the computational process of this considerable system for machine vision systems. HMAX is known as one of the best computational models which have been inspired by hierarchical structure of the human visual cortex. During learning stage of the HMAX, a large number of small part of training images, called patches, are extracted at random positions. These patches are in various sizes and orientations. The random selection of patches, not only degrades the performance but also increases the computational complexity of HMAX-based object recognition systems. In this paper, we focus on this drawback and propose a new method based on information theory to select more relevant patches and remove redundant ones. The proposed method is developed for a face categorization task in which the purpose is to detect the presence or absence of faces in real world images. The performance of the proposed method has been evaluated on face image database CalTech101 and its recognition rate is superior to the original HMAX by more than 5%.
{"title":"Enhanced Brain Inspired Model for Face Categorization Using Mutual Information Maximization","authors":"Mohammad Jazlaeiyan, Sanaz Seyedin, S. A. Motamedi","doi":"10.1109/ICBME.2018.8703599","DOIUrl":"https://doi.org/10.1109/ICBME.2018.8703599","url":null,"abstract":"Human visual system can robustly and simply recognize complex objects in cluttered natural scenes. So far, numerous computational models have been developed to mimic the computational process of this considerable system for machine vision systems. HMAX is known as one of the best computational models which have been inspired by hierarchical structure of the human visual cortex. During learning stage of the HMAX, a large number of small part of training images, called patches, are extracted at random positions. These patches are in various sizes and orientations. The random selection of patches, not only degrades the performance but also increases the computational complexity of HMAX-based object recognition systems. In this paper, we focus on this drawback and propose a new method based on information theory to select more relevant patches and remove redundant ones. The proposed method is developed for a face categorization task in which the purpose is to detect the presence or absence of faces in real world images. The performance of the proposed method has been evaluated on face image database CalTech101 and its recognition rate is superior to the original HMAX by more than 5%.","PeriodicalId":338286,"journal":{"name":"2018 25th National and 3rd International Iranian Conference on Biomedical Engineering (ICBME)","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130580641","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}
Pub Date : 2018-11-01DOI: 10.1109/ICBME.2018.8703577
Farnaz Morshedlou, N. Ravanshad, H. Rezaee-Dehsorkh
In this paper an ultra-low power current-mode analog circuit is proposed for detecting QRS complexes from the ECG signal. An accurate low-power operation is obtained by using a non-linear energy operator and designing all the transistors in subthreshold region. For improving the performance of the circuit, three filters with very-low cutoff frequencies are utilized which do not require large capacitors and so do not occupy large area. Two of the three filters are used for realizing onset detection method and the other is used for estimating a threshold which is required for QRS detection. Simulating over the entire MIT/BIH arrhythmia database shows the acceptable values of 98.69% for the average accuracy, 99.24% for the sensitivity and 99.38% for the positive prediction. The proposed circuit is implemented in 0.18 µm CMOS technology with a 1.8 V supply voltage. Using the proposed circuit, no analog-to-digital converter is required to be used which save a considerable portion of the power and the area. Consuming a 71 nW power, the proposed circuit is suitable for wearable and implantable ECG monitoring applications.
{"title":"A Low-Power Current-Mode Analog QRS-Detection Circuit for Wearable ECG Sensors","authors":"Farnaz Morshedlou, N. Ravanshad, H. Rezaee-Dehsorkh","doi":"10.1109/ICBME.2018.8703577","DOIUrl":"https://doi.org/10.1109/ICBME.2018.8703577","url":null,"abstract":"In this paper an ultra-low power current-mode analog circuit is proposed for detecting QRS complexes from the ECG signal. An accurate low-power operation is obtained by using a non-linear energy operator and designing all the transistors in subthreshold region. For improving the performance of the circuit, three filters with very-low cutoff frequencies are utilized which do not require large capacitors and so do not occupy large area. Two of the three filters are used for realizing onset detection method and the other is used for estimating a threshold which is required for QRS detection. Simulating over the entire MIT/BIH arrhythmia database shows the acceptable values of 98.69% for the average accuracy, 99.24% for the sensitivity and 99.38% for the positive prediction. The proposed circuit is implemented in 0.18 µm CMOS technology with a 1.8 V supply voltage. Using the proposed circuit, no analog-to-digital converter is required to be used which save a considerable portion of the power and the area. Consuming a 71 nW power, the proposed circuit is suitable for wearable and implantable ECG monitoring applications.","PeriodicalId":338286,"journal":{"name":"2018 25th National and 3rd International Iranian Conference on Biomedical Engineering (ICBME)","volume":"48 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131964989","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}
Pub Date : 2018-11-01DOI: 10.1109/icbme.2018.8703497
{"title":"ICBME 2018 Program","authors":"","doi":"10.1109/icbme.2018.8703497","DOIUrl":"https://doi.org/10.1109/icbme.2018.8703497","url":null,"abstract":"","PeriodicalId":338286,"journal":{"name":"2018 25th National and 3rd International Iranian Conference on Biomedical Engineering (ICBME)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124770955","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}
Pub Date : 2018-11-01DOI: 10.1109/ICBME.2018.8703573
Sajad Shafiekhani, S. Rahbar, Fahimeh Akbarian, A. Jafari
Uncertainty as inherent feature of Tumor-Immune system causes unpredictable behaviors of this complex network. Uncertainty of tumor-immune system is due to randomness in cell-cell interactions, vague, incomplete data, dynamic properties of tumor (including, e.g., extracellular ligands, mutation types, vascular status, phenotypic distribution) which are varying during time and patient-dependent properties. Fuzzy Stochastic Petri Net (FSPN) can capture this uncertainty that combine Stochastic Petri Net (SPN) with fuzzy sets. SPN model the dynamics of this complex network with regarding randomness in cell interactions and fuzzy sets consider fuzziness. FSPN of this study associate a fuzzy number instead of crisp number to kinetic parameter of SPN. Tumor-immune system of this study consider interactions of Tumor cells, Cytotoxic T lymphocytes (CTL) and Myeloid-derived suppressor cell as major component of system. CTLs are produced by immune activation of cytotoxic T cells and MDSCs augment in pathological situations such as cancer that acquire strong immunosuppressive activities. The dynamical behavior of tumor-immune system with regarding uncertain kinetic parameters is achieved by FSPN and the steady state behavior of the system with regarding fuzzy uncertain kinetic parameters is computed. The model simulates the dynamics of the cells in tumor escape and tumor elimination phases. FSPN proves that with increasing uncertainty of model parameters, the uncertainty of cell dynamics also increases. We showed that if the model kinetic parameters be a fuzzy number with a triangular membership function, the uncertainty interval of the cells is triangular in relation to the alpha-cuts.This method can be used for modeling and simulation of any biological network with uncertain information.
{"title":"Fuzzy Stochastic Petri Net with Uncertain Kinetic Parameters for Modeling Tumor-Immune System","authors":"Sajad Shafiekhani, S. Rahbar, Fahimeh Akbarian, A. Jafari","doi":"10.1109/ICBME.2018.8703573","DOIUrl":"https://doi.org/10.1109/ICBME.2018.8703573","url":null,"abstract":"Uncertainty as inherent feature of Tumor-Immune system causes unpredictable behaviors of this complex network. Uncertainty of tumor-immune system is due to randomness in cell-cell interactions, vague, incomplete data, dynamic properties of tumor (including, e.g., extracellular ligands, mutation types, vascular status, phenotypic distribution) which are varying during time and patient-dependent properties. Fuzzy Stochastic Petri Net (FSPN) can capture this uncertainty that combine Stochastic Petri Net (SPN) with fuzzy sets. SPN model the dynamics of this complex network with regarding randomness in cell interactions and fuzzy sets consider fuzziness. FSPN of this study associate a fuzzy number instead of crisp number to kinetic parameter of SPN. Tumor-immune system of this study consider interactions of Tumor cells, Cytotoxic T lymphocytes (CTL) and Myeloid-derived suppressor cell as major component of system. CTLs are produced by immune activation of cytotoxic T cells and MDSCs augment in pathological situations such as cancer that acquire strong immunosuppressive activities. The dynamical behavior of tumor-immune system with regarding uncertain kinetic parameters is achieved by FSPN and the steady state behavior of the system with regarding fuzzy uncertain kinetic parameters is computed. The model simulates the dynamics of the cells in tumor escape and tumor elimination phases. FSPN proves that with increasing uncertainty of model parameters, the uncertainty of cell dynamics also increases. We showed that if the model kinetic parameters be a fuzzy number with a triangular membership function, the uncertainty interval of the cells is triangular in relation to the alpha-cuts.This method can be used for modeling and simulation of any biological network with uncertain information.","PeriodicalId":338286,"journal":{"name":"2018 25th National and 3rd International Iranian Conference on Biomedical Engineering (ICBME)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123082364","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}
Pub Date : 2018-11-01DOI: 10.1109/ICBME.2018.8703574
M. Mahbod, M. Asgari
Porous biomaterials are known as one of the new materials which are widely used and especially appropriate for bone interfacing components. Besides providing a proper area for bone ingrowth, their mechanical properties mimic properties of bone. It has been entrenched that porous biomaterials can be produced considering defined representative volume elements (RVE) by recent developments in additive manufacturing. In this paper a novel functionally graded porous material is introduced based on a new RVE. In order to calculate the mechanical properties (elastic modulus, yield stress and Poisson's ratio), theoretical solutions are developed. Furthermore, a numerical investigation via ANSYS Workbench has been performed to validate the analytical solution. As the results show the obtained properties of the proposed structures are suitable for application of bone implant. Furthermore, the mechanical properties of each layer of structure have been calculated.
{"title":"Mechanical Properties of Functionally Graded Biomaterials in Bone Replacement; Analytical and Numerical Solution","authors":"M. Mahbod, M. Asgari","doi":"10.1109/ICBME.2018.8703574","DOIUrl":"https://doi.org/10.1109/ICBME.2018.8703574","url":null,"abstract":"Porous biomaterials are known as one of the new materials which are widely used and especially appropriate for bone interfacing components. Besides providing a proper area for bone ingrowth, their mechanical properties mimic properties of bone. It has been entrenched that porous biomaterials can be produced considering defined representative volume elements (RVE) by recent developments in additive manufacturing. In this paper a novel functionally graded porous material is introduced based on a new RVE. In order to calculate the mechanical properties (elastic modulus, yield stress and Poisson's ratio), theoretical solutions are developed. Furthermore, a numerical investigation via ANSYS Workbench has been performed to validate the analytical solution. As the results show the obtained properties of the proposed structures are suitable for application of bone implant. Furthermore, the mechanical properties of each layer of structure have been calculated.","PeriodicalId":338286,"journal":{"name":"2018 25th National and 3rd International Iranian Conference on Biomedical Engineering (ICBME)","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116994570","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}
Pub Date : 2018-11-01DOI: 10.1109/ICBME.2018.8703593
Arash Dehghani, S. Seyyedsalehi
In this paper, various structures and methods of Deep Artificial Neural Networks (DNN) will be evaluated and compared for the purpose of continuous Persian speech recognition. One of the first models of neural networks used in speech recognition applications were fully connected Neural Networks (FCNNs) and, consequently, Deep Neural Networks (DNNs). Although these models have better performance compared to GMM / HMM models, they do not have the proper structure to model local speech information. Convolutional Neural Network (CNN) is a good option for modeling the local structure of biological signals, including speech signals. Another issue that Deep Artificial Neural Networks face, is the convergence of networks on training data. The main inhibitor of convergence is the presence of local minima in the process of training. Deep Neural Network Pre-training methods, despite a large amount of computing, are powerful tools for crossing the local minima. But the use of appropriate neuronal models in the network structure seems to be a better solution to this problem. The Rectified Linear Unit neuronal model and the Maxout model are the most suitable neuronal models presented to this date. Several experiments were carried out to evaluate the performance of the methods and structures mentioned. After verifying the proper functioning of these methods, a combination of all models was implemented on FARSDAT speech database for continuous speech recognition. The results obtained from the experiments show that the combined model (CMDNN) improves the performance of ANNs in speech recognition versus the pre-trained fully connected NNs with sigmoid neurons by about 3%.
{"title":"Performance Evaluation of Deep Convolutional Maxout Neural Network in Speech Recognition","authors":"Arash Dehghani, S. Seyyedsalehi","doi":"10.1109/ICBME.2018.8703593","DOIUrl":"https://doi.org/10.1109/ICBME.2018.8703593","url":null,"abstract":"In this paper, various structures and methods of Deep Artificial Neural Networks (DNN) will be evaluated and compared for the purpose of continuous Persian speech recognition. One of the first models of neural networks used in speech recognition applications were fully connected Neural Networks (FCNNs) and, consequently, Deep Neural Networks (DNNs). Although these models have better performance compared to GMM / HMM models, they do not have the proper structure to model local speech information. Convolutional Neural Network (CNN) is a good option for modeling the local structure of biological signals, including speech signals. Another issue that Deep Artificial Neural Networks face, is the convergence of networks on training data. The main inhibitor of convergence is the presence of local minima in the process of training. Deep Neural Network Pre-training methods, despite a large amount of computing, are powerful tools for crossing the local minima. But the use of appropriate neuronal models in the network structure seems to be a better solution to this problem. The Rectified Linear Unit neuronal model and the Maxout model are the most suitable neuronal models presented to this date. Several experiments were carried out to evaluate the performance of the methods and structures mentioned. After verifying the proper functioning of these methods, a combination of all models was implemented on FARSDAT speech database for continuous speech recognition. The results obtained from the experiments show that the combined model (CMDNN) improves the performance of ANNs in speech recognition versus the pre-trained fully connected NNs with sigmoid neurons by about 3%.","PeriodicalId":338286,"journal":{"name":"2018 25th National and 3rd International Iranian Conference on Biomedical Engineering (ICBME)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129172230","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}
Pub Date : 2018-11-01DOI: 10.1109/ICBME.2018.8703571
Mohammad Behzady, H. Mohammadi, M. Farid
The focus of this study is to obtain the material properties of human common carotid artery (CCA). A hyper-elastic strain energy model is used to predict mechanical behavior of arterial wall from an inflation/deflation test on the human CCA intact wall. For this purpose, two methods are used in order to identify arterial material parameters: analytical and inverse finite element method. An optimization algorithm, based on aforementioned methods, is employed to find optimal parameters that have the best fitness with experimental data. The final outcome of the present study is to compare the reliability of aforementioned methods to identify material properties of modeling human CCA in FE problems.
{"title":"Anisotropic material properties of human left common carotid artery using inverse finite element and analytical methods","authors":"Mohammad Behzady, H. Mohammadi, M. Farid","doi":"10.1109/ICBME.2018.8703571","DOIUrl":"https://doi.org/10.1109/ICBME.2018.8703571","url":null,"abstract":"The focus of this study is to obtain the material properties of human common carotid artery (CCA). A hyper-elastic strain energy model is used to predict mechanical behavior of arterial wall from an inflation/deflation test on the human CCA intact wall. For this purpose, two methods are used in order to identify arterial material parameters: analytical and inverse finite element method. An optimization algorithm, based on aforementioned methods, is employed to find optimal parameters that have the best fitness with experimental data. The final outcome of the present study is to compare the reliability of aforementioned methods to identify material properties of modeling human CCA in FE problems.","PeriodicalId":338286,"journal":{"name":"2018 25th National and 3rd International Iranian Conference on Biomedical Engineering (ICBME)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131619942","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}
Pub Date : 2018-11-01DOI: 10.1109/ICBME.2018.8703598
M. Sepehrnia, Golnoush Abaei, Zahra Khosromirza, Faezeh RooghaniYazdi
Simultaneous using of MEMS (Micro Electro Mechanical Systems) and nanotechnology systems in the cooling of micro-scale electrical equipment has attracted researchers in recent years. In the present study, cooling of medical equipment with electronic board is discussed. For this purpose, water and water-diamond nanofluid with a volume fraction of 1%, 2%, 3% and 4% are used as a coolant of micro-scale cooling system. Coolants are pumped into heat sink at pressures of 5, 15, 25 and 35 kPa. The electronic chip on the board is embedded in the base plate of heat sink and generates uniform heat flux of 85kW/m2. The governing equations have been solved using finite volume method based on finite element. The results show that utilizing water-diamond nanofluid compared to water improves the cooling process so that utilizing water-diamond nanofluid with volume fraction of 4% improves the cooling process between 4.46% and 7.22%. Moreover, increasing pressure drop from 5 kPa to 35 kPa improves cooling indexes between 17.86% and 25.52%. Moreover, designing radial basis function artificial neural network shows good agreement between numerical simulation and predicted results.
{"title":"Numerical Simulation and Designing Artificial Neural Network for Water-Diamond Nanofluid Flow for Micro-Scale Cooling of Medical Equipment","authors":"M. Sepehrnia, Golnoush Abaei, Zahra Khosromirza, Faezeh RooghaniYazdi","doi":"10.1109/ICBME.2018.8703598","DOIUrl":"https://doi.org/10.1109/ICBME.2018.8703598","url":null,"abstract":"Simultaneous using of MEMS (Micro Electro Mechanical Systems) and nanotechnology systems in the cooling of micro-scale electrical equipment has attracted researchers in recent years. In the present study, cooling of medical equipment with electronic board is discussed. For this purpose, water and water-diamond nanofluid with a volume fraction of 1%, 2%, 3% and 4% are used as a coolant of micro-scale cooling system. Coolants are pumped into heat sink at pressures of 5, 15, 25 and 35 kPa. The electronic chip on the board is embedded in the base plate of heat sink and generates uniform heat flux of 85kW/m2. The governing equations have been solved using finite volume method based on finite element. The results show that utilizing water-diamond nanofluid compared to water improves the cooling process so that utilizing water-diamond nanofluid with volume fraction of 4% improves the cooling process between 4.46% and 7.22%. Moreover, increasing pressure drop from 5 kPa to 35 kPa improves cooling indexes between 17.86% and 25.52%. Moreover, designing radial basis function artificial neural network shows good agreement between numerical simulation and predicted results.","PeriodicalId":338286,"journal":{"name":"2018 25th National and 3rd International Iranian Conference on Biomedical Engineering (ICBME)","volume":"290 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123272134","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}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：