Pub Date : 2019-05-01DOI: 10.1109/ICASERT.2019.8934580
Md. Raihan Uddin, Kh. Mohaimenul Kabir, Md. Taslim Arefin
Cloud computing is a spirited topic in this epoch where IOT introducing the modern lifestyle. These embrace cost-effectiveness, time savings and the actual arrangement of computing properties. Conversely, in Cloud Computing privacy and security is a big issue where there are many kinds of thread and attack are working rapidly. In the context, the best cryptographic method AES algorithm and AI-based method ANN have chosen to work for the enhancement of the security where cloud computing demands the highest priority. In this case, this paper is proposing the highly advanced two-step security layer for cloud computing. Primarily, AES provides for the first layer security of the first stratum. In the AES algorithm, the execution is dependent on the key size of the algorithm when the number of rounds to be accomplished. A MATLAB code is developed for plaintext encryption and cipher text decryption. Experiments are conducted to measure execution times. ANN is a method of computation which is biologically stimulated. These only look like the parallel computation generated which are the basics of human learning by the biological neural network. Iris and Finger recognition is implemented using MATLAB through ANN. The paper demonstrated the great proficiency of the proposed system for the user purpose.
{"title":"Artificial Neural Network Inducement for Enhancement of Cloud Computing Security","authors":"Md. Raihan Uddin, Kh. Mohaimenul Kabir, Md. Taslim Arefin","doi":"10.1109/ICASERT.2019.8934580","DOIUrl":"https://doi.org/10.1109/ICASERT.2019.8934580","url":null,"abstract":"Cloud computing is a spirited topic in this epoch where IOT introducing the modern lifestyle. These embrace cost-effectiveness, time savings and the actual arrangement of computing properties. Conversely, in Cloud Computing privacy and security is a big issue where there are many kinds of thread and attack are working rapidly. In the context, the best cryptographic method AES algorithm and AI-based method ANN have chosen to work for the enhancement of the security where cloud computing demands the highest priority. In this case, this paper is proposing the highly advanced two-step security layer for cloud computing. Primarily, AES provides for the first layer security of the first stratum. In the AES algorithm, the execution is dependent on the key size of the algorithm when the number of rounds to be accomplished. A MATLAB code is developed for plaintext encryption and cipher text decryption. Experiments are conducted to measure execution times. ANN is a method of computation which is biologically stimulated. These only look like the parallel computation generated which are the basics of human learning by the biological neural network. Iris and Finger recognition is implemented using MATLAB through ANN. The paper demonstrated the great proficiency of the proposed system for the user purpose.","PeriodicalId":6613,"journal":{"name":"2019 1st International Conference on Advances in Science, Engineering and Robotics Technology (ICASERT)","volume":"102 1","pages":"1-6"},"PeriodicalIF":0.0,"publicationDate":"2019-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"75831063","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 : 2019-05-01DOI: 10.1109/ICASERT.2019.8934662
Kazi Md. Munim, Iyolita Islam, Moumita Sarker, M. Islam
Cities where water supply system follows trivial analog system like Dhaka city, a twenty-four hours monitoring is required to start the water pump immediately when water is available in the main water supply line. A significant amount of water can be wasted only for the reason of overflowing the water tank. Thus, the aim of this paper is to propose an automated water pumping system to minimize the wastage of time, money, labor and water loss. A high-fidelity prototype system was designed and developed using the Arduino Uno, water pump, potentiometer and relay switch; and able to control its operation automatically with respect to the availability and amount of water in the main water supply line and the reserve water. An evaluation study was also conducted to assess the availability and reliability of the system. The evaluation results showed that the proposed system is reliable, available and cost-effective.
{"title":"Towards Developing an Intelligent Automated Water Pumping System for Dhaka City","authors":"Kazi Md. Munim, Iyolita Islam, Moumita Sarker, M. Islam","doi":"10.1109/ICASERT.2019.8934662","DOIUrl":"https://doi.org/10.1109/ICASERT.2019.8934662","url":null,"abstract":"Cities where water supply system follows trivial analog system like Dhaka city, a twenty-four hours monitoring is required to start the water pump immediately when water is available in the main water supply line. A significant amount of water can be wasted only for the reason of overflowing the water tank. Thus, the aim of this paper is to propose an automated water pumping system to minimize the wastage of time, money, labor and water loss. A high-fidelity prototype system was designed and developed using the Arduino Uno, water pump, potentiometer and relay switch; and able to control its operation automatically with respect to the availability and amount of water in the main water supply line and the reserve water. An evaluation study was also conducted to assess the availability and reliability of the system. The evaluation results showed that the proposed system is reliable, available and cost-effective.","PeriodicalId":6613,"journal":{"name":"2019 1st International Conference on Advances in Science, Engineering and Robotics Technology (ICASERT)","volume":"23 1","pages":"1-5"},"PeriodicalIF":0.0,"publicationDate":"2019-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"74436895","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 : 2019-05-01DOI: 10.1109/ICASERT.2019.8934587
Md. Abu Sayeed, H. Rouf, Mohd. Rezaul Hasan, K. Hussain
Fabrication of Zinc Selenide (ZnSe) thin film having different thickness has been performed on glass substrate using thermal vacuum evaporation technique by evaporating ZnSe powder and is further characterized by X-ray diffractometer (XRD) and UV-VIS-NIR spectrophotometer. XRD patterns revealed that ZnSe thin film has face centered cubic (fcc) structure with variable miller indices at maximum X-ray intensity as the thickness changes. Substrate temperature is fixed at 290°C and all films are annealed for 60 minutes at 300°C. We have got peak value of intensity in XRD patterns which drops as the thickness of ZnSe thin film reduces. Optical properties like transmittance, refractive index, energy bandgap and reflectance have also been extracted in both simulation and experiment and found promising results. Transmittance in near-infrared region for all the films are greater than 63% in simulation and fewer less in experiment, variable reflectance of (7-31)%, optical bandgap from 2.44 eV to 2.64 eV and fluctuation in refractive index from 2.31 to 2.70 as the film thickness changes. Optical bandgap goes wider for higher thickness films and gets lower as the film thickness decreases.
采用热真空蒸发技术，利用蒸发ZnSe粉末在玻璃基板上制备了不同厚度的硒化锌(ZnSe)薄膜，并用x射线衍射仪(XRD)和紫外-可见-近红外分光光度计对其进行了表征。XRD谱图表明，随着厚度的变化，ZnSe薄膜在最大x射线强度下具有面心立方(fcc)结构，米勒指数随厚度的变化而变化。衬底温度固定在290°C，所有薄膜在300°C退火60分钟。得到了随ZnSe薄膜厚度减小而减小的x射线衍射强度峰值。在模拟和实验中也提取了透光率、折射率、能带隙和反射率等光学特性，并取得了令人满意的结果。所有薄膜在近红外区的透射率在模拟中均大于63%，实验中均小于63%，可变反射率为(7 ~ 31)%，光学带隙在2.44 eV ~ 2.64 eV之间，折射率随薄膜厚度变化在2.31 ~ 2.70之间波动。薄膜厚度越大，光带隙越宽，薄膜厚度越小，光带隙越小。
{"title":"Thickness Dependency of Zinc Selenide (ZnSe) Thin Film Deposited By Vacuum Evaporation Method","authors":"Md. Abu Sayeed, H. Rouf, Mohd. Rezaul Hasan, K. Hussain","doi":"10.1109/ICASERT.2019.8934587","DOIUrl":"https://doi.org/10.1109/ICASERT.2019.8934587","url":null,"abstract":"Fabrication of Zinc Selenide (ZnSe) thin film having different thickness has been performed on glass substrate using thermal vacuum evaporation technique by evaporating ZnSe powder and is further characterized by X-ray diffractometer (XRD) and UV-VIS-NIR spectrophotometer. XRD patterns revealed that ZnSe thin film has face centered cubic (fcc) structure with variable miller indices at maximum X-ray intensity as the thickness changes. Substrate temperature is fixed at 290°C and all films are annealed for 60 minutes at 300°C. We have got peak value of intensity in XRD patterns which drops as the thickness of ZnSe thin film reduces. Optical properties like transmittance, refractive index, energy bandgap and reflectance have also been extracted in both simulation and experiment and found promising results. Transmittance in near-infrared region for all the films are greater than 63% in simulation and fewer less in experiment, variable reflectance of (7-31)%, optical bandgap from 2.44 eV to 2.64 eV and fluctuation in refractive index from 2.31 to 2.70 as the film thickness changes. Optical bandgap goes wider for higher thickness films and gets lower as the film thickness decreases.","PeriodicalId":6613,"journal":{"name":"2019 1st International Conference on Advances in Science, Engineering and Robotics Technology (ICASERT)","volume":"13 10","pages":"1-5"},"PeriodicalIF":0.0,"publicationDate":"2019-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"72565842","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 : 2019-05-01DOI: 10.1109/ICASERT.2019.8934547
Md. Khirul Alam Titu, S. Hasan, M. Adnan
In this work, by employing self-consistent solver we study Capacitance-Voltage (C-V) characteristics and the threshold voltage variation of p-type Rectangular Gate Junctionless Field Effect Transistor (RG-JLFET) and Double Gate Junctionless Field Effect Transistor (DG-JLFET). The selfconsistent solver solves Schrodinger-Poisson equations with appropriate boundary conditions and takes wave function penetration and other quantum mechanical effects into account. We compare the effect of device parameter variation (such as channel thickness, oxide thickness and doping concentration) on threshold voltage control for both transistor structures. Physical explanations of the found results are also provided.
{"title":"Impact of Increased Quantum Confinement on Gate Capacitance and Threshold Voltage of p Channel Junctionless Transistor","authors":"Md. Khirul Alam Titu, S. Hasan, M. Adnan","doi":"10.1109/ICASERT.2019.8934547","DOIUrl":"https://doi.org/10.1109/ICASERT.2019.8934547","url":null,"abstract":"In this work, by employing self-consistent solver we study Capacitance-Voltage (C-V) characteristics and the threshold voltage variation of p-type Rectangular Gate Junctionless Field Effect Transistor (RG-JLFET) and Double Gate Junctionless Field Effect Transistor (DG-JLFET). The selfconsistent solver solves Schrodinger-Poisson equations with appropriate boundary conditions and takes wave function penetration and other quantum mechanical effects into account. We compare the effect of device parameter variation (such as channel thickness, oxide thickness and doping concentration) on threshold voltage control for both transistor structures. Physical explanations of the found results are also provided.","PeriodicalId":6613,"journal":{"name":"2019 1st International Conference on Advances in Science, Engineering and Robotics Technology (ICASERT)","volume":"7 1","pages":"1-4"},"PeriodicalIF":0.0,"publicationDate":"2019-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"78196878","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 : 2019-05-01DOI: 10.1109/ICASERT.2019.8934576
Adharaa Neelim Dewanjee, Quazi Delwar Hossain, M. S. Arefin
The biometric method which is involved with defining pattern of movement of human limbs is called Gait. Though gait has a fixed rhythmic pattern, in case of people who are affected with neurological disease such as- Parkinson's disease (PD) the gait pattern gets distorted from normal gait pattern. In this paper, temporal variables of gait cycles are analyzed to determine the deficit in the gait cycle in PD patients. Gait cycle of 10 PD patients and 10 Controlled subjects are examined in this paper. A comparative analysis was done in respect of temporal variables such as- Single Limb Support Time and Double Limb Support Time. From the examination and investigation, it is apparent that the temporal factors of the gait cycle of PD patients are sufficiently changed in regard to the controlled subjects, all the more explicitly PD patients invest more energy in the two limbs than a single limb of a gait cycle which is absolutely in switch of the controlled subject.
{"title":"Temporal Variables Disorder of The Gait Cycle in Parkinson’s Disease","authors":"Adharaa Neelim Dewanjee, Quazi Delwar Hossain, M. S. Arefin","doi":"10.1109/ICASERT.2019.8934576","DOIUrl":"https://doi.org/10.1109/ICASERT.2019.8934576","url":null,"abstract":"The biometric method which is involved with defining pattern of movement of human limbs is called Gait. Though gait has a fixed rhythmic pattern, in case of people who are affected with neurological disease such as- Parkinson's disease (PD) the gait pattern gets distorted from normal gait pattern. In this paper, temporal variables of gait cycles are analyzed to determine the deficit in the gait cycle in PD patients. Gait cycle of 10 PD patients and 10 Controlled subjects are examined in this paper. A comparative analysis was done in respect of temporal variables such as- Single Limb Support Time and Double Limb Support Time. From the examination and investigation, it is apparent that the temporal factors of the gait cycle of PD patients are sufficiently changed in regard to the controlled subjects, all the more explicitly PD patients invest more energy in the two limbs than a single limb of a gait cycle which is absolutely in switch of the controlled subject.","PeriodicalId":6613,"journal":{"name":"2019 1st International Conference on Advances in Science, Engineering and Robotics Technology (ICASERT)","volume":"48 1","pages":"1-6"},"PeriodicalIF":0.0,"publicationDate":"2019-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"78231692","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 : 2019-05-01DOI: 10.1109/ICASERT.2019.8934628
Umid Kumar Dey, Md. Sajjatul Islam
One of the worst epidemics in the history of mankind is the deadly disease known as cancer. There are several types of cancer and the one that is more commonly heard of these days is leukemia. There are two types of leukemia – acute myeloid leukemia (AML) and acute lymphocytic leukemia (ALL) – and the purpose of this study is to take into account the gene expression data of several people and predict what type of leukemia they have by using three machine learning algorithms, XGBoost, Random Forest Classification and Artificial Neural Networks. The dataset’s dimensionality was reduced using principal component analysis (PCA) before using the algorithms on them.
{"title":"Genetic Expression Analysis To Detect Type Of Leukemia Using Machine Learning","authors":"Umid Kumar Dey, Md. Sajjatul Islam","doi":"10.1109/ICASERT.2019.8934628","DOIUrl":"https://doi.org/10.1109/ICASERT.2019.8934628","url":null,"abstract":"One of the worst epidemics in the history of mankind is the deadly disease known as cancer. There are several types of cancer and the one that is more commonly heard of these days is leukemia. There are two types of leukemia – acute myeloid leukemia (AML) and acute lymphocytic leukemia (ALL) – and the purpose of this study is to take into account the gene expression data of several people and predict what type of leukemia they have by using three machine learning algorithms, XGBoost, Random Forest Classification and Artificial Neural Networks. The dataset’s dimensionality was reduced using principal component analysis (PCA) before using the algorithms on them.","PeriodicalId":6613,"journal":{"name":"2019 1st International Conference on Advances in Science, Engineering and Robotics Technology (ICASERT)","volume":"4 1","pages":"1-6"},"PeriodicalIF":0.0,"publicationDate":"2019-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"78449756","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 : 2019-05-01DOI: 10.1109/ICASERT.2019.8934546
Misbah Ul Hoque, T. M. Shahriar Sazzad, A. Farabi, I. Hosen, Mursheda Akter Somi
Cancer is a kind of cell that develops out of control of the regular drives that normalizes growth. Breast cancer is one of the deadly forms of cancers for the human. Initial detection of cancerous tissues is likely to monitor the patient’s strength to deal with the disease and live more. Electronic modalities are applied to diagnose breast cancers. Due to low cost and safety, ultrasound scanning is considered as one of the most frequently used electronic modalities for breast cancer detection. This research study proposed an automated approach for breast cancer detection using ultrasound gray-scale images. To this end, enhancement operation was used at the beginning to minimize the grayscale color shifts. Median filter was used to facilitate better segmentation removing maximum unwanted noises. Threshold-based segmentation (Threshold based OTSU) was used as the test images used in this study are gray-scale images. Finally, necessary feature information that is used in the pathology laboratory by pathology experts is used in this study to identify the ROI (Region of interests) to detect breast cancer tissues. This study proposed approach achieved an average accuracy rate of 93.11%. The depicted experimental outcomes of the proposed approach outperform other contemporary existing available approaches in terms of accuracy while maintaining the medical experts’ acceptable accuracy rate.
癌症是一种失去正常生长控制的细胞。乳腺癌是人类致命的癌症之一。对癌变组织的初步检测有可能监测到患者应对疾病的力量和活得更久。电子模式被用于诊断乳腺癌。由于低成本和安全性，超声扫描被认为是乳腺癌检测中最常用的电子方式之一。本研究提出了一种利用超声灰度图像自动检测乳腺癌的方法。为此，在开始时使用增强操作来最小化灰度色移。中值滤波用于更好的分割，去除最大的不需要的噪声。由于本研究使用的测试图像为灰度图像，因此采用基于阈值的分割(Threshold based OTSU)。最后，本研究使用病理专家在病理实验室中使用的必要特征信息来识别ROI (Region of interest)，以检测乳腺癌组织。本研究提出的方法平均准确率为93.11%。所描述的实验结果提出的方法优于其他当代现有的方法在准确性方面，同时保持医学专家可接受的准确率。
{"title":"An Automated Approach to Detect Breast Cancer Tissue Using Ultrasound Images","authors":"Misbah Ul Hoque, T. M. Shahriar Sazzad, A. Farabi, I. Hosen, Mursheda Akter Somi","doi":"10.1109/ICASERT.2019.8934546","DOIUrl":"https://doi.org/10.1109/ICASERT.2019.8934546","url":null,"abstract":"Cancer is a kind of cell that develops out of control of the regular drives that normalizes growth. Breast cancer is one of the deadly forms of cancers for the human. Initial detection of cancerous tissues is likely to monitor the patient’s strength to deal with the disease and live more. Electronic modalities are applied to diagnose breast cancers. Due to low cost and safety, ultrasound scanning is considered as one of the most frequently used electronic modalities for breast cancer detection. This research study proposed an automated approach for breast cancer detection using ultrasound gray-scale images. To this end, enhancement operation was used at the beginning to minimize the grayscale color shifts. Median filter was used to facilitate better segmentation removing maximum unwanted noises. Threshold-based segmentation (Threshold based OTSU) was used as the test images used in this study are gray-scale images. Finally, necessary feature information that is used in the pathology laboratory by pathology experts is used in this study to identify the ROI (Region of interests) to detect breast cancer tissues. This study proposed approach achieved an average accuracy rate of 93.11%. The depicted experimental outcomes of the proposed approach outperform other contemporary existing available approaches in terms of accuracy while maintaining the medical experts’ acceptable accuracy rate.","PeriodicalId":6613,"journal":{"name":"2019 1st International Conference on Advances in Science, Engineering and Robotics Technology (ICASERT)","volume":"133 1","pages":"1-4"},"PeriodicalIF":0.0,"publicationDate":"2019-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76111023","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 : 2019-05-01DOI: 10.1109/ICASERT.2019.8934453
Raian Islam, Murad Mehrab Abrar, Farhatul Hassan, Sifat Adnan
In recent years Organic Solar Cells have become a prominent topic of research to achieve an optimum efficiency at low cost. By using the GPVDM software on this paper, we have analyzed the effect on power conversion efficiency, changing simultaneously both the polymers and blending layer thickness of P3HT:PCBM based solar cell. Our main goal is to find which layer change keeps the power conversion efficiency output better. After comparing them, the result shows that setting the active layer (P3HT:PCBM) in an optimum fixed value and varying the polymer layer (PEDOT:PSS) gives a better output of PCE. In our paper, from the data in both cases, The highest efficiency is 4.50 percent where P3HT:PCBM layer thickness is 2.2×10-7 m and PEDOT:PSS layer thickness is 1×10-7 m.
近年来，以低成本获得最佳效率的有机太阳能电池已成为研究的热点。本文利用GPVDM软件，分析了P3HT:PCBM基太阳能电池聚合物和共混层厚度同时改变对功率转换效率的影响。我们的主要目标是找出哪一层的变化使功率转换效率输出更好。结果表明，将活性层(P3HT:PCBM)设置为最佳固定值，改变聚合物层(PEDOT:PSS)可以获得更好的PCE输出，本文从两种情况下的数据来看，当P3HT:PCBM层厚度为2.2×10-7 m, PEDOT:PSS层厚度为1×10-7 m时，效率最高为4.50%。
{"title":"Layer thickness effect on power conversion efficiency of a P3HT:PCBM based organicsolar cell","authors":"Raian Islam, Murad Mehrab Abrar, Farhatul Hassan, Sifat Adnan","doi":"10.1109/ICASERT.2019.8934453","DOIUrl":"https://doi.org/10.1109/ICASERT.2019.8934453","url":null,"abstract":"In recent years Organic Solar Cells have become a prominent topic of research to achieve an optimum efficiency at low cost. By using the GPVDM software on this paper, we have analyzed the effect on power conversion efficiency, changing simultaneously both the polymers and blending layer thickness of P3HT:PCBM based solar cell. Our main goal is to find which layer change keeps the power conversion efficiency output better. After comparing them, the result shows that setting the active layer (P3HT:PCBM) in an optimum fixed value and varying the polymer layer (PEDOT:PSS) gives a better output of PCE. In our paper, from the data in both cases, The highest efficiency is 4.50 percent where P3HT:PCBM layer thickness is 2.2×10-7 m and PEDOT:PSS layer thickness is 1×10-7 m.","PeriodicalId":6613,"journal":{"name":"2019 1st International Conference on Advances in Science, Engineering and Robotics Technology (ICASERT)","volume":"45 1","pages":"1-3"},"PeriodicalIF":0.0,"publicationDate":"2019-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80278130","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 : 2019-05-01DOI: 10.1109/ICASERT.2019.8934588
Pratik Deb, Mohammad Nooruddin, Md. Shajahan Badshah
Electrocardiogram (ECG) is a graphical representation of the electrical activity of the heart which is obtained by placing various electrodes on some specific positions of the body surface of the subject. Abnormalities in the ECG signal of a patient may indicate cardiac diseases that need to be attended by physicians on an urgent basis. Hence, it is necessary to detect an abnormal ECG for the betterment of the patient. Such a method to classify ECG signals whether they are normal or abnormal is developed in this work. Angina, Bundle Branch Block, Cardiomyopathy Heart Failure, Dysrhythmia, Myocardial Hypertrophy, Myocardial Infarction, Myocarditis, Valvular Heart Disease: all these cardiac conditions have been classified as abnormal ECG signal in our work. First, statistical features like skewness, kurtosis, standard deviation of detail and approximation coefficients of the Daubechies wavelet (db10) of order 5 for a number of abnormal and normal ECG signals obtained in the feature extraction stage. Secondly, Support Vector Machine (SVM) was used for classification which was trained by the features extracted in the first stage. Finally, the accuracy, sensitivity, specificity of this method was checked by testing the SVM with 36 signals obtained from MIT-BIH Normal Sinus Rhythm Database and 36 signals from PTB Diagnostic ECG Database which yielded an accuracy, sensitivity, specificity 98.61%, 97.37%, 97.22% respectively.
{"title":"Detection of Abnormal Electrocardiogram (ECG) Using Wavelet Decomposition and Support Vector Machine (SVM)","authors":"Pratik Deb, Mohammad Nooruddin, Md. Shajahan Badshah","doi":"10.1109/ICASERT.2019.8934588","DOIUrl":"https://doi.org/10.1109/ICASERT.2019.8934588","url":null,"abstract":"Electrocardiogram (ECG) is a graphical representation of the electrical activity of the heart which is obtained by placing various electrodes on some specific positions of the body surface of the subject. Abnormalities in the ECG signal of a patient may indicate cardiac diseases that need to be attended by physicians on an urgent basis. Hence, it is necessary to detect an abnormal ECG for the betterment of the patient. Such a method to classify ECG signals whether they are normal or abnormal is developed in this work. Angina, Bundle Branch Block, Cardiomyopathy Heart Failure, Dysrhythmia, Myocardial Hypertrophy, Myocardial Infarction, Myocarditis, Valvular Heart Disease: all these cardiac conditions have been classified as abnormal ECG signal in our work. First, statistical features like skewness, kurtosis, standard deviation of detail and approximation coefficients of the Daubechies wavelet (db10) of order 5 for a number of abnormal and normal ECG signals obtained in the feature extraction stage. Secondly, Support Vector Machine (SVM) was used for classification which was trained by the features extracted in the first stage. Finally, the accuracy, sensitivity, specificity of this method was checked by testing the SVM with 36 signals obtained from MIT-BIH Normal Sinus Rhythm Database and 36 signals from PTB Diagnostic ECG Database which yielded an accuracy, sensitivity, specificity 98.61%, 97.37%, 97.22% respectively.","PeriodicalId":6613,"journal":{"name":"2019 1st International Conference on Advances in Science, Engineering and Robotics Technology (ICASERT)","volume":"91 1","pages":"1-8"},"PeriodicalIF":0.0,"publicationDate":"2019-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80482893","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 : 2019-05-01DOI: 10.1109/ICASERT.2019.8934933
M. Al-Amin, Tasfia Anika Bushra, Md Nazmul Hoq
Potato is one of the most used crops in the world and 2nd most important crop in Bangladesh. Our economy is largely affected by the production of potato. But its production is hampered due to different diseases of potato leaves. These diseases decrease production and increase the price of potatoes. Our objective is to develop an automated system which will predict the potato disease and helps farmers to take necessary steps. In this work, we implemented a model based on Convolutional Neural Network (CNN) which provides 98.33% accurate result in predicting different diseases of potatoes. This is the maximum accuracy gained for only potato disease prediction to the best of our understanding. The system is cost effective, less time consuming and provides an efficient way of predicting potato diseases from leaves. This will help the farmers and lead our country towards a digital agricultural system.
{"title":"Prediction of Potato Disease from Leaves using Deep Convolution Neural Network towards a Digital Agricultural System","authors":"M. Al-Amin, Tasfia Anika Bushra, Md Nazmul Hoq","doi":"10.1109/ICASERT.2019.8934933","DOIUrl":"https://doi.org/10.1109/ICASERT.2019.8934933","url":null,"abstract":"Potato is one of the most used crops in the world and 2nd most important crop in Bangladesh. Our economy is largely affected by the production of potato. But its production is hampered due to different diseases of potato leaves. These diseases decrease production and increase the price of potatoes. Our objective is to develop an automated system which will predict the potato disease and helps farmers to take necessary steps. In this work, we implemented a model based on Convolutional Neural Network (CNN) which provides 98.33% accurate result in predicting different diseases of potatoes. This is the maximum accuracy gained for only potato disease prediction to the best of our understanding. The system is cost effective, less time consuming and provides an efficient way of predicting potato diseases from leaves. This will help the farmers and lead our country towards a digital agricultural system.","PeriodicalId":6613,"journal":{"name":"2019 1st International Conference on Advances in Science, Engineering and Robotics Technology (ICASERT)","volume":"89 1","pages":"1-5"},"PeriodicalIF":0.0,"publicationDate":"2019-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79120655","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：