Pub Date : 2019-07-01DOI: 10.1109/IC4ME247184.2019.9036700
Md. Azizul Hakim, Md. Zahid Hasan, Md. Mahabur Alam, M. Hasan, M. Hasan
Brain stroke become a serious cardiovascular and cerebral disease causes of human death. Precisely predicting stroke effect from a set of predictive attributes may classify high-risk patients and guide cure approaches, leading to reduce relative incidence. In respect to, we have collected the information regarding brain stroke patient’s data from five renowned hospitals in Bangladesh with connectivity in patients with acute thalamic ischemic stroke (melanoma), Atypical Nevus (cancer risk) and Common Nevus (No cancer risk). In this work, we propose an ensemble based Modified Bootstrap Aggregating (Bagging) technique for pattern classification. Existing bagging algorithm, can usually progress the performance of a single classifier. However, they typically need larger space as well as quite time-consuming predictions. However, our proposed accuracy based pruning bagging method can improve the classification performance and reduce ensemble size. In general, our proposed modified bagging technique is more appropriate than traditional bagging technique for the prediction of brain stroke disease patients with greater accuracy of 96%.
{"title":"An Efficient Modified Bagging Method for Early Prediction of Brain Stroke","authors":"Md. Azizul Hakim, Md. Zahid Hasan, Md. Mahabur Alam, M. Hasan, M. Hasan","doi":"10.1109/IC4ME247184.2019.9036700","DOIUrl":"https://doi.org/10.1109/IC4ME247184.2019.9036700","url":null,"abstract":"Brain stroke become a serious cardiovascular and cerebral disease causes of human death. Precisely predicting stroke effect from a set of predictive attributes may classify high-risk patients and guide cure approaches, leading to reduce relative incidence. In respect to, we have collected the information regarding brain stroke patient’s data from five renowned hospitals in Bangladesh with connectivity in patients with acute thalamic ischemic stroke (melanoma), Atypical Nevus (cancer risk) and Common Nevus (No cancer risk). In this work, we propose an ensemble based Modified Bootstrap Aggregating (Bagging) technique for pattern classification. Existing bagging algorithm, can usually progress the performance of a single classifier. However, they typically need larger space as well as quite time-consuming predictions. However, our proposed accuracy based pruning bagging method can improve the classification performance and reduce ensemble size. In general, our proposed modified bagging technique is more appropriate than traditional bagging technique for the prediction of brain stroke disease patients with greater accuracy of 96%.","PeriodicalId":368690,"journal":{"name":"2019 International Conference on Computer, Communication, Chemical, Materials and Electronic Engineering (IC4ME2)","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115914125","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 : 2019-07-01DOI: 10.1109/IC4ME247184.2019.9036538
Muzammal Hoque, Md. Mehedi Hashan Jony, Mehedi Hasan, M. H. Kabir
3D printing refers to the processes in which materials joined or solidified under computer control to create a three-dimensional object. A machine that allows this process is known as a 3D printer. It has several components. The major components of a 3D printer are frame, Head movement mechanics, (Stepper) Motors, The print head/extruder, Firmware, 3D Software, etc. In this research, it was attempted to describe the design and construction process of a Fused Deposition Modeling (FDM) 3D printer with the help of a traditional 3D printer. The 3D printer was used to print different-designed parts of our targeted 3D printer designed by Computer-Aided Design (CAD) software. After the construction and firmware installation, four different prints of different sizes were done and the resulting outputs were analyzed.
{"title":"Design and Implementation of an FDM Based 3D Printer","authors":"Muzammal Hoque, Md. Mehedi Hashan Jony, Mehedi Hasan, M. H. Kabir","doi":"10.1109/IC4ME247184.2019.9036538","DOIUrl":"https://doi.org/10.1109/IC4ME247184.2019.9036538","url":null,"abstract":"3D printing refers to the processes in which materials joined or solidified under computer control to create a three-dimensional object. A machine that allows this process is known as a 3D printer. It has several components. The major components of a 3D printer are frame, Head movement mechanics, (Stepper) Motors, The print head/extruder, Firmware, 3D Software, etc. In this research, it was attempted to describe the design and construction process of a Fused Deposition Modeling (FDM) 3D printer with the help of a traditional 3D printer. The 3D printer was used to print different-designed parts of our targeted 3D printer designed by Computer-Aided Design (CAD) software. After the construction and firmware installation, four different prints of different sizes were done and the resulting outputs were analyzed.","PeriodicalId":368690,"journal":{"name":"2019 International Conference on Computer, Communication, Chemical, Materials and Electronic Engineering (IC4ME2)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130737812","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 : 2019-07-01DOI: 10.1109/IC4ME247184.2019.9036651
Shawkh Ibne Rashid, Md. Azharul Islam, Md. Al Mehedi Hasan
This paper represents a combined model of convolutional neural network (CNN) and support vector machine (SVM) for traffic sign recognition. This model was built by training a CNN model. Once the CNN model is fully trained the output from the later layers of CNN can be used as features. These features were then fed into SVM for classification purpose. Three different models of CNN: modified version of LeNet, AlexNet and ResNet-50 were considered to build three CNN-SVM models. The integrated model of Resnet50 and SVM seems to perform better than ResNet-50 while the other two merged models of Lenet and Alexnet performed worse than their corresponding CNN models. One reason of this can be ResNet-50 having a shallow classification part consisting of only one fully connected layer while modified version of LeNet and AlexNet have 3 and 4 fully connected layers respectively. This combined approach provides for a good comparison between SVM and CNN as classifiers since the features used in both these classifiers are same. So a comparative analysis among three different CNN models and their corresponding integrated models is shown. In our analysis, we considered different measurement metrices like accuracy, precision, recall and F1 score. We used German Traffic Sign Detection Benchmark (GTSRB) dataset. This dataset gives access to a wide range of traffic sign images.
{"title":"Traffic Sign Recognition by Integrating Convolutional Neural Network and Support Vector Machine","authors":"Shawkh Ibne Rashid, Md. Azharul Islam, Md. Al Mehedi Hasan","doi":"10.1109/IC4ME247184.2019.9036651","DOIUrl":"https://doi.org/10.1109/IC4ME247184.2019.9036651","url":null,"abstract":"This paper represents a combined model of convolutional neural network (CNN) and support vector machine (SVM) for traffic sign recognition. This model was built by training a CNN model. Once the CNN model is fully trained the output from the later layers of CNN can be used as features. These features were then fed into SVM for classification purpose. Three different models of CNN: modified version of LeNet, AlexNet and ResNet-50 were considered to build three CNN-SVM models. The integrated model of Resnet50 and SVM seems to perform better than ResNet-50 while the other two merged models of Lenet and Alexnet performed worse than their corresponding CNN models. One reason of this can be ResNet-50 having a shallow classification part consisting of only one fully connected layer while modified version of LeNet and AlexNet have 3 and 4 fully connected layers respectively. This combined approach provides for a good comparison between SVM and CNN as classifiers since the features used in both these classifiers are same. So a comparative analysis among three different CNN models and their corresponding integrated models is shown. In our analysis, we considered different measurement metrices like accuracy, precision, recall and F1 score. We used German Traffic Sign Detection Benchmark (GTSRB) dataset. This dataset gives access to a wide range of traffic sign images.","PeriodicalId":368690,"journal":{"name":"2019 International Conference on Computer, Communication, Chemical, Materials and Electronic Engineering (IC4ME2)","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131404534","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 : 2019-07-01DOI: 10.1109/IC4ME247184.2019.9036704
Rahul Saha Joy, Mir Mohammad Adil, Md. Abdullah Al Mahmood
The effects of temperatures on the growth and morphology of the nanostructured materials from ferrocene is observed. The process carried in an open air condition instead of autoclave which is difficult to maintain. Here, we have observed the variation of heating temperatures in the growth of CNSs by carrying out the reaction between ferrocene and ammonium chloride in a solvent free condition for 45mins. Carbon nanostructures of different form yielded from this reaction at 230 (CNS-230), 240 (CNS-240), 250 (CNS-250) and 260 (CNS-260) were characterized by means of field emission scanning electron microscopy (FESEM) coupled with energy-dispersive x-ray (EDX), X-Ray Diffraction spectroscopy(XRD), Fourier transform infrared (FTIR) and ultraviolet–visible (UV–Vis) spectroscopy. The FESEM images obtained shows long carbon tube with diameter ranging from 70-160nm and varying with temperatures. While EDX confirms the very high percentage of carbon in the samples. FTIR spectra of all the nanostructures confirmed the presence of functional group such as C=C, corresponding to amorphous carbon. UV–Vis spectra shows no absorption peak in the visible region suggested that the sample is amorphous in nature, which is also strongly supported by XRD of the synthesized nanostructure.
{"title":"Low temperature synthesis of carbon nanostructure and effect of temperatures on the growth of amorphous carbon nanostructure.","authors":"Rahul Saha Joy, Mir Mohammad Adil, Md. Abdullah Al Mahmood","doi":"10.1109/IC4ME247184.2019.9036704","DOIUrl":"https://doi.org/10.1109/IC4ME247184.2019.9036704","url":null,"abstract":"The effects of temperatures on the growth and morphology of the nanostructured materials from ferrocene is observed. The process carried in an open air condition instead of autoclave which is difficult to maintain. Here, we have observed the variation of heating temperatures in the growth of CNSs by carrying out the reaction between ferrocene and ammonium chloride in a solvent free condition for 45mins. Carbon nanostructures of different form yielded from this reaction at 230 (CNS-230), 240 (CNS-240), 250 (CNS-250) and 260 (CNS-260) were characterized by means of field emission scanning electron microscopy (FESEM) coupled with energy-dispersive x-ray (EDX), X-Ray Diffraction spectroscopy(XRD), Fourier transform infrared (FTIR) and ultraviolet–visible (UV–Vis) spectroscopy. The FESEM images obtained shows long carbon tube with diameter ranging from 70-160nm and varying with temperatures. While EDX confirms the very high percentage of carbon in the samples. FTIR spectra of all the nanostructures confirmed the presence of functional group such as C=C, corresponding to amorphous carbon. UV–Vis spectra shows no absorption peak in the visible region suggested that the sample is amorphous in nature, which is also strongly supported by XRD of the synthesized nanostructure.","PeriodicalId":368690,"journal":{"name":"2019 International Conference on Computer, Communication, Chemical, Materials and Electronic Engineering (IC4ME2)","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126733525","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 : 2019-07-01DOI: 10.1109/IC4ME247184.2019.9036532
Kangkan Bhakta, Niloy Sikder, A. Nahid, M. M. M. Islam
Motors are the driving force of our industrial world, as they power approximately 85% of all rotating machines. This revolutionary invention has been through radical changes before entering into the commercial industries, and their present forms are very reliable, to say the least. However, despite being so robust, induction motors are not entirely fault-proof and are more vulnerable to the internal faults than the external ones. Among the internal faults, certain types of bearing faults are more frequent, and their effects range from various performance-related issues to hard motor breakdowns. Fortunately, the recent advancements in the fields of Digital Signal Processing and Machine Learning allow us to detect these bearing faults and Figure out their origins, which in turn enables us to preserve their health and take measures against breakdowns. Through vibration analysis, this paper proposes a powerful method to detect these faults and differentiate among them based on the location of their occurrence within the bearing. Utilizing a well-known signal processing technique called Discrete Cosine Transform and Decision Tree classifier, this method is capable of classifying the motor bearing states with a 99.4% accuracy.
{"title":"Rotating Element Bearing Fault Diagnosis Using Discrete Cosine Transform and Supervised Machine Learning Algorithm","authors":"Kangkan Bhakta, Niloy Sikder, A. Nahid, M. M. M. Islam","doi":"10.1109/IC4ME247184.2019.9036532","DOIUrl":"https://doi.org/10.1109/IC4ME247184.2019.9036532","url":null,"abstract":"Motors are the driving force of our industrial world, as they power approximately 85% of all rotating machines. This revolutionary invention has been through radical changes before entering into the commercial industries, and their present forms are very reliable, to say the least. However, despite being so robust, induction motors are not entirely fault-proof and are more vulnerable to the internal faults than the external ones. Among the internal faults, certain types of bearing faults are more frequent, and their effects range from various performance-related issues to hard motor breakdowns. Fortunately, the recent advancements in the fields of Digital Signal Processing and Machine Learning allow us to detect these bearing faults and Figure out their origins, which in turn enables us to preserve their health and take measures against breakdowns. Through vibration analysis, this paper proposes a powerful method to detect these faults and differentiate among them based on the location of their occurrence within the bearing. Utilizing a well-known signal processing technique called Discrete Cosine Transform and Decision Tree classifier, this method is capable of classifying the motor bearing states with a 99.4% accuracy.","PeriodicalId":368690,"journal":{"name":"2019 International Conference on Computer, Communication, Chemical, Materials and Electronic Engineering (IC4ME2)","volume":"205 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115909837","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 : 2019-07-01DOI: 10.1109/IC4ME247184.2019.9036513
Md. Rawshan Habib, K. Ahmed, Naureen Khan, Mahbubur Rahman Kiran, M. Habib, M. Hasan, Omar Farrok
In this paper, an automatic grass cutting machine is designed and implemented that uses solar energy as its primary source. The proposed grass cutter is lightweight and portable. It has two major parts: one is a motor-powered base and the other is cutting blades with motor. Its default mood is automatic although it can be operated manually if necessary. It can detect the position of grass by a color sensor through specified band of green color signal and is able to move automatically towards the grass by its motorized controlled base. As soon as the motor driven cutting blade comes close to the grass, it starts cutting and continue until all grasses around it is being cut down. The prototype of the grass cutter is tested experimentally. The test result proves that, the grass cutter successfully performs its operation. Two degree-of-freedom PID controllers are proposed to control the motor speed of the prototype.
{"title":"PID Controller Based Automatic Solar PowerDriven Grass Cutting Machine","authors":"Md. Rawshan Habib, K. Ahmed, Naureen Khan, Mahbubur Rahman Kiran, M. Habib, M. Hasan, Omar Farrok","doi":"10.1109/IC4ME247184.2019.9036513","DOIUrl":"https://doi.org/10.1109/IC4ME247184.2019.9036513","url":null,"abstract":"In this paper, an automatic grass cutting machine is designed and implemented that uses solar energy as its primary source. The proposed grass cutter is lightweight and portable. It has two major parts: one is a motor-powered base and the other is cutting blades with motor. Its default mood is automatic although it can be operated manually if necessary. It can detect the position of grass by a color sensor through specified band of green color signal and is able to move automatically towards the grass by its motorized controlled base. As soon as the motor driven cutting blade comes close to the grass, it starts cutting and continue until all grasses around it is being cut down. The prototype of the grass cutter is tested experimentally. The test result proves that, the grass cutter successfully performs its operation. Two degree-of-freedom PID controllers are proposed to control the motor speed of the prototype.","PeriodicalId":368690,"journal":{"name":"2019 International Conference on Computer, Communication, Chemical, Materials and Electronic Engineering (IC4ME2)","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122057276","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 : 2019-07-01DOI: 10.1109/IC4ME247184.2019.9036506
S. C. Mohonta, A. K. Sarkar
The level of competency of playing cricket defensive drive was measured by using double pendulum model. Three defensive drives by three right-handed batters were recorded in the bat and wrist mounted inertial sensors. The sensor recorded acceleration profiles were tried to match with those obtained by modeling the drives with double pendulum dynamics imposing the initial conditions at start of each drives. In the analysis, the movement of the bat was modeled as the lower pendulum and the wrist as the upper pendulum of the double pendulum model. Phase portrait derivative method was used to analyze each drives in the pendulum dynamics to quantify the competency of the action for the drives. The method showed that the better competency of two batters (error 2.5% and 7.4%) compared to third one (error 13.9%) can easily be identified observing the statistical features (i. e. standard deviation of the bat velocity, ratio of major to minor axis of the phase portrait curve, null hypothesis between sensor data and data from the double pendulum model) extracted from the sensor and double pendulum model. Competency test can be a useful tool for cricket coaching environment; furthermore, incorporation of mathematics in cricket batting might add a new dimension in batting research.
{"title":"Competency Test in Cricket Defensive Drive using Double Pendulum Dynamics","authors":"S. C. Mohonta, A. K. Sarkar","doi":"10.1109/IC4ME247184.2019.9036506","DOIUrl":"https://doi.org/10.1109/IC4ME247184.2019.9036506","url":null,"abstract":"The level of competency of playing cricket defensive drive was measured by using double pendulum model. Three defensive drives by three right-handed batters were recorded in the bat and wrist mounted inertial sensors. The sensor recorded acceleration profiles were tried to match with those obtained by modeling the drives with double pendulum dynamics imposing the initial conditions at start of each drives. In the analysis, the movement of the bat was modeled as the lower pendulum and the wrist as the upper pendulum of the double pendulum model. Phase portrait derivative method was used to analyze each drives in the pendulum dynamics to quantify the competency of the action for the drives. The method showed that the better competency of two batters (error 2.5% and 7.4%) compared to third one (error 13.9%) can easily be identified observing the statistical features (i. e. standard deviation of the bat velocity, ratio of major to minor axis of the phase portrait curve, null hypothesis between sensor data and data from the double pendulum model) extracted from the sensor and double pendulum model. Competency test can be a useful tool for cricket coaching environment; furthermore, incorporation of mathematics in cricket batting might add a new dimension in batting research.","PeriodicalId":368690,"journal":{"name":"2019 International Conference on Computer, Communication, Chemical, Materials and Electronic Engineering (IC4ME2)","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116766606","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 : 2019-07-01DOI: 10.1109/IC4ME247184.2019.9036571
M. K. Kundu, M. Sarkar, A. S. M. Badrudduza, Dilip Kumar Sarker
This paper concentrates on the analysis of security performance for transmitting confidential data from a source to multiple receivers over Generalized-K fading multicasting channel in the presence of multiple eavesdroppers. All the terminals are equipped with single antenna and all the channels are Generalized-K fading based on mixture gamma distribution. In order to investigate the effects of fading parameters imposed on the Generalized-K fading with mixture gamma distribution, we derive the closed-form analytical expressions for the probability of non-zero secrecy multicast capacity, ergodic secrecy multicast capacity and the secure outage probability for multicasting &. The derived analytical expressions are presented in terms of the fading parameters of Generalized-K fading with mixture gamma distribution so that they are helpful to understand the insight, how the security in multicasting can be enhanced adjusting the parameters of Generalized-K fading channels. Monte-Carlo Simulations have also been performed to validate the analytical results.
{"title":"Secure Wireless Multicasting with Mixture Gamma Distribution for Generalized-K Fading Channels","authors":"M. K. Kundu, M. Sarkar, A. S. M. Badrudduza, Dilip Kumar Sarker","doi":"10.1109/IC4ME247184.2019.9036571","DOIUrl":"https://doi.org/10.1109/IC4ME247184.2019.9036571","url":null,"abstract":"This paper concentrates on the analysis of security performance for transmitting confidential data from a source to multiple receivers over Generalized-K fading multicasting channel in the presence of multiple eavesdroppers. All the terminals are equipped with single antenna and all the channels are Generalized-K fading based on mixture gamma distribution. In order to investigate the effects of fading parameters imposed on the Generalized-K fading with mixture gamma distribution, we derive the closed-form analytical expressions for the probability of non-zero secrecy multicast capacity, ergodic secrecy multicast capacity and the secure outage probability for multicasting &. The derived analytical expressions are presented in terms of the fading parameters of Generalized-K fading with mixture gamma distribution so that they are helpful to understand the insight, how the security in multicasting can be enhanced adjusting the parameters of Generalized-K fading channels. Monte-Carlo Simulations have also been performed to validate the analytical results.","PeriodicalId":368690,"journal":{"name":"2019 International Conference on Computer, Communication, Chemical, Materials and Electronic Engineering (IC4ME2)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123295881","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 : 2019-07-01DOI: 10.1109/IC4ME247184.2019.9036627
M. Hasan, Md. Rakibul Haque, Mir Md. Jahangir Kabir
One of the most wide-spreading diseases among women is Breast Cancer. For this reason, a proper diagnosis is necessary for designating necessary treatment. Using the previous information about patients, diagnosis is being performed by various machine learning algorithms. As the data are getting bigger, it is becoming more necessary to extract the useful information from the huge pile of information. In this paper, we have used the Wisconsin diagnostic breast cancer dataset (WDBC) and SEER 2017 Breast Cancer Dataset. Then we have used Principal component analysis in order to extract useful features. After that, we have classified the reduced datasets using multi-layer perceptron (MLP) and convolution neural network (CNN). Then we have provided a comparative comparison of our model for both the reduced datasets. Our MLP model has achieved an accuracy of 99.1% on reduced WDBC dataset and 89.3% on SEER 2017 Breast Cancer dataset whereas CNN Model has achieved 96.4% on reduced WDBC dataset and 88.3% on SEER 2017 Breast Cancer Dataset.
{"title":"Breast Cancer Diagnosis Models Using PCA and Different Neural Network Architectures","authors":"M. Hasan, Md. Rakibul Haque, Mir Md. Jahangir Kabir","doi":"10.1109/IC4ME247184.2019.9036627","DOIUrl":"https://doi.org/10.1109/IC4ME247184.2019.9036627","url":null,"abstract":"One of the most wide-spreading diseases among women is Breast Cancer. For this reason, a proper diagnosis is necessary for designating necessary treatment. Using the previous information about patients, diagnosis is being performed by various machine learning algorithms. As the data are getting bigger, it is becoming more necessary to extract the useful information from the huge pile of information. In this paper, we have used the Wisconsin diagnostic breast cancer dataset (WDBC) and SEER 2017 Breast Cancer Dataset. Then we have used Principal component analysis in order to extract useful features. After that, we have classified the reduced datasets using multi-layer perceptron (MLP) and convolution neural network (CNN). Then we have provided a comparative comparison of our model for both the reduced datasets. Our MLP model has achieved an accuracy of 99.1% on reduced WDBC dataset and 89.3% on SEER 2017 Breast Cancer dataset whereas CNN Model has achieved 96.4% on reduced WDBC dataset and 88.3% on SEER 2017 Breast Cancer Dataset.","PeriodicalId":368690,"journal":{"name":"2019 International Conference on Computer, Communication, Chemical, Materials and Electronic Engineering (IC4ME2)","volume":"64 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122539051","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 : 2019-07-01DOI: 10.1109/IC4ME247184.2019.9036494
Md Elias Uddin, T. H. Mojumder, S.M. Nasif Shams
Solar cell efficiency is subjected to some innate variables such as Open Circuit Voltage (Voc), Short Circuit Current (Isc), and Fill Factor (FF). Parasitical elements have effect on these variables. Resistive elements are known shunt resistances and series resistance. Shunt resistance in solar panel happens due to deficiencies. Volume shunts can occur due to impurities like metal particles defilement or aluminum particle defilement while making grid fingers are nearly inconceivable to remove except damaging experimental the solar cell. In many cases, frequently occurred edge shunts caused by cracks, spots can be eliminated with different available techniques. During the making of solar cell, edge isolation process can be applied on the solar cells that affects IV characteristics of solar cell, which is critical to the efficiency. In this research work, wet chemical etching method by combination of Hydrochloric acid, Nitric acid and Nitric acid (HNA solution). This combined solution is used for experimental procedure. In experimental results, it is observed that etching with the acid solution improves the IV characteristics of solar cells and hence it ameliorates the power curves. Efficiency before etching solar cells was 3.17% and 3.90%. After etching the solar cell efficiency increase up to 5.53% and 5.31% respectively.
{"title":"Wet Chemical etching for edge Isolation of Solar cell using HNA","authors":"Md Elias Uddin, T. H. Mojumder, S.M. Nasif Shams","doi":"10.1109/IC4ME247184.2019.9036494","DOIUrl":"https://doi.org/10.1109/IC4ME247184.2019.9036494","url":null,"abstract":"Solar cell efficiency is subjected to some innate variables such as Open Circuit Voltage (Voc), Short Circuit Current (Isc), and Fill Factor (FF). Parasitical elements have effect on these variables. Resistive elements are known shunt resistances and series resistance. Shunt resistance in solar panel happens due to deficiencies. Volume shunts can occur due to impurities like metal particles defilement or aluminum particle defilement while making grid fingers are nearly inconceivable to remove except damaging experimental the solar cell. In many cases, frequently occurred edge shunts caused by cracks, spots can be eliminated with different available techniques. During the making of solar cell, edge isolation process can be applied on the solar cells that affects IV characteristics of solar cell, which is critical to the efficiency. In this research work, wet chemical etching method by combination of Hydrochloric acid, Nitric acid and Nitric acid (HNA solution). This combined solution is used for experimental procedure. In experimental results, it is observed that etching with the acid solution improves the IV characteristics of solar cells and hence it ameliorates the power curves. Efficiency before etching solar cells was 3.17% and 3.90%. After etching the solar cell efficiency increase up to 5.53% and 5.31% respectively.","PeriodicalId":368690,"journal":{"name":"2019 International Conference on Computer, Communication, Chemical, Materials and Electronic Engineering (IC4ME2)","volume":"148 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121378065","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：