Pub Date : 2021-07-13DOI: 10.1109/ICIAS49414.2021.9642670
Nur Aainaa Nadirah Azlan, I. Elamvazuthi, T. Tang, Cheng-Kai Lu
One of the cancers that gives high fatality rates in human life is breast cancer. The current method used to detect breast cancer needs radiologists, which makes it costly and time-consuming. A possible solution is to detect it early, which can be done by computer-aided diagnosis technologies. An end-to-end system that could automatically detect breast cancer is described in this paper. From the mammographic images, it was first undergone the pre-processing stages for noise elimination. The law's mask was then applied to the preprocessed image to filter out the secondary features further. The filtered image was segmented by the active contour to obtain the breast region before being fed into a deep convolutional neural network for feature extraction. Principle Component Analysis (PCA) technique was then applied to select the necessary features as input to the Support Vector Machine (SVM) for determining the class of cells (normal or abnormal). Lastly, k-fold cross-validation techniques were executed to validate the results and obtained the average reading for both training and testing datasets. The proposed system was tested on the Digital Database for Screening Mammography (DDSM) and Mammographic Image Analysis Society (MIAS) dataset, and attained 97.50%, 96.67%, 98.33%, and 0.99 for accuracy, sensitivity, specificity, and area under curve, respectively.
{"title":"Breast Cancer Detection by Hybrid Techniques based on Deep Learning Networks","authors":"Nur Aainaa Nadirah Azlan, I. Elamvazuthi, T. Tang, Cheng-Kai Lu","doi":"10.1109/ICIAS49414.2021.9642670","DOIUrl":"https://doi.org/10.1109/ICIAS49414.2021.9642670","url":null,"abstract":"One of the cancers that gives high fatality rates in human life is breast cancer. The current method used to detect breast cancer needs radiologists, which makes it costly and time-consuming. A possible solution is to detect it early, which can be done by computer-aided diagnosis technologies. An end-to-end system that could automatically detect breast cancer is described in this paper. From the mammographic images, it was first undergone the pre-processing stages for noise elimination. The law's mask was then applied to the preprocessed image to filter out the secondary features further. The filtered image was segmented by the active contour to obtain the breast region before being fed into a deep convolutional neural network for feature extraction. Principle Component Analysis (PCA) technique was then applied to select the necessary features as input to the Support Vector Machine (SVM) for determining the class of cells (normal or abnormal). Lastly, k-fold cross-validation techniques were executed to validate the results and obtained the average reading for both training and testing datasets. The proposed system was tested on the Digital Database for Screening Mammography (DDSM) and Mammographic Image Analysis Society (MIAS) dataset, and attained 97.50%, 96.67%, 98.33%, and 0.99 for accuracy, sensitivity, specificity, and area under curve, respectively.","PeriodicalId":212635,"journal":{"name":"2020 8th International Conference on Intelligent and Advanced Systems (ICIAS)","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134269549","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 : 2021-07-13DOI: 10.1109/ICIAS49414.2021.9642628
Christopher Teh Jun Qian, M. Drieberg, S. Soeung
Internet of Things (IoT) is a massive network of connected devices that enables data sharing and analysis for extracting valuable information. Many industries have started to integrate IoT into their devices to increase their businesses’ competitiveness. IoT devices which consume less power, can be potentially powered up using an energy harvesting system instead of batteries. A photovoltaic (PV) panel converts light energy into electrical energy is used to harvest the power. To predict the behaviour of PV panel, an accurate model is required. Most of the manufacturers provide values of three characteristic points (open circuit point, short circuit point, and maximum power point) at standard test conditions (STC) condition. However, STC condition is not always achieved in reality. Therefore, this paper presents the methodology for modeling an accurate one diode model with two resistors under different irradiance with the help of characteristic points translation technique. The proposed model is applied on a commercial PV panel. Three characteristic points of the model are obtained and validate with the datasheet values. The results achieve a good agreement with a difference below than 5 %. The proposed model shows an accuracy improvement when compared to the existing models.
{"title":"One Diode PV Modeling Under Varying Irradiance","authors":"Christopher Teh Jun Qian, M. Drieberg, S. Soeung","doi":"10.1109/ICIAS49414.2021.9642628","DOIUrl":"https://doi.org/10.1109/ICIAS49414.2021.9642628","url":null,"abstract":"Internet of Things (IoT) is a massive network of connected devices that enables data sharing and analysis for extracting valuable information. Many industries have started to integrate IoT into their devices to increase their businesses’ competitiveness. IoT devices which consume less power, can be potentially powered up using an energy harvesting system instead of batteries. A photovoltaic (PV) panel converts light energy into electrical energy is used to harvest the power. To predict the behaviour of PV panel, an accurate model is required. Most of the manufacturers provide values of three characteristic points (open circuit point, short circuit point, and maximum power point) at standard test conditions (STC) condition. However, STC condition is not always achieved in reality. Therefore, this paper presents the methodology for modeling an accurate one diode model with two resistors under different irradiance with the help of characteristic points translation technique. The proposed model is applied on a commercial PV panel. Three characteristic points of the model are obtained and validate with the datasheet values. The results achieve a good agreement with a difference below than 5 %. The proposed model shows an accuracy improvement when compared to the existing models.","PeriodicalId":212635,"journal":{"name":"2020 8th International Conference on Intelligent and Advanced Systems (ICIAS)","volume":"39 3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132977174","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 : 2021-07-13DOI: 10.1109/ICIAS49414.2021.9642675
Omid Rezaei, Mahyar Alinejad, Seyed Ashkan Nejati, B. Chong
As lithium-ion batteries have nonlinearities and also uncertainties in parameter identification in their dynamical model, accurate estimation of SoC requires robust and nonlinear estimators. Using a sliding mode observer, this paper presents an optimal adaptive estimator to measure the state of charge (SoC) of lithium-ion batteries (LIB). The conventional sliding mode observers have chattering phenomena and prolong convergence time in their performance, but the sliding mode observer proposed in this paper includes an adaptive gain which causes less chattering and convergence time. The simulation results and software in the loop (SIL) validation confirm the effectiveness of the proposed estimation method of SoC.
{"title":"An optimized adaptive estimation of state of charge for Lithium-ion battery based on sliding mode observer for electric vehicle application","authors":"Omid Rezaei, Mahyar Alinejad, Seyed Ashkan Nejati, B. Chong","doi":"10.1109/ICIAS49414.2021.9642675","DOIUrl":"https://doi.org/10.1109/ICIAS49414.2021.9642675","url":null,"abstract":"As lithium-ion batteries have nonlinearities and also uncertainties in parameter identification in their dynamical model, accurate estimation of SoC requires robust and nonlinear estimators. Using a sliding mode observer, this paper presents an optimal adaptive estimator to measure the state of charge (SoC) of lithium-ion batteries (LIB). The conventional sliding mode observers have chattering phenomena and prolong convergence time in their performance, but the sliding mode observer proposed in this paper includes an adaptive gain which causes less chattering and convergence time. The simulation results and software in the loop (SIL) validation confirm the effectiveness of the proposed estimation method of SoC.","PeriodicalId":212635,"journal":{"name":"2020 8th International Conference on Intelligent and Advanced Systems (ICIAS)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129333644","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 : 2021-07-13DOI: 10.1109/ICIAS49414.2021.9642531
M. Rehman, P. Nallagownden, M. A. Bhayo, Z. Baharudin, Maveeya Baba
This paper presents the design, development and realization of a field mill for accurately measuring the DC field. In this research study, a typical capacitor, comprising of one fixed electrode and another rotating electrode is used. A controlled DC motor based on PWM (Pulse Width Modulation) technique is used which drives the rotating electrode of the capacitor. The ATmega8 microcontroller is employed, mainly, for analog to digital conversion, PWM generation and for reading the output of the photoelectric sensor. The programming of the ATmega8 microcontroller is done in C-language; WinAVR tool is used for the programming. The performance of the developed field mill is analyzed by creating the DC electric field in the laboratory environment with the help of parallel plate capacitor. A regulated HVDC supply setup is also built for parallel plate capacitor. The developed field mill was tested under positive as well as negative polarity. The proposed field mill is portable, it can be used anywhere to measure the DC field. The development details, mechanical, electrical and electronic components used, and the experimental results are presented in this paper. The overall results show that the developed field mill device can measure the DC field up to the range of ± 65 kV/m, with standard deviation of only ± 2.42%.
{"title":"Design of a Field Mill Device for Measuring the High Voltage DC Fields","authors":"M. Rehman, P. Nallagownden, M. A. Bhayo, Z. Baharudin, Maveeya Baba","doi":"10.1109/ICIAS49414.2021.9642531","DOIUrl":"https://doi.org/10.1109/ICIAS49414.2021.9642531","url":null,"abstract":"This paper presents the design, development and realization of a field mill for accurately measuring the DC field. In this research study, a typical capacitor, comprising of one fixed electrode and another rotating electrode is used. A controlled DC motor based on PWM (Pulse Width Modulation) technique is used which drives the rotating electrode of the capacitor. The ATmega8 microcontroller is employed, mainly, for analog to digital conversion, PWM generation and for reading the output of the photoelectric sensor. The programming of the ATmega8 microcontroller is done in C-language; WinAVR tool is used for the programming. The performance of the developed field mill is analyzed by creating the DC electric field in the laboratory environment with the help of parallel plate capacitor. A regulated HVDC supply setup is also built for parallel plate capacitor. The developed field mill was tested under positive as well as negative polarity. The proposed field mill is portable, it can be used anywhere to measure the DC field. The development details, mechanical, electrical and electronic components used, and the experimental results are presented in this paper. The overall results show that the developed field mill device can measure the DC field up to the range of ± 65 kV/m, with standard deviation of only ± 2.42%.","PeriodicalId":212635,"journal":{"name":"2020 8th International Conference on Intelligent and Advanced Systems (ICIAS)","volume":"69 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129875115","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 : 2021-07-13DOI: 10.1109/ICIAS49414.2021.9642661
U. M. Al-Saggaf, Abdelaziz Botalb, M. Moinuddin, S. Alfakeh, Syed Saad Azhar Ali, Tang Tong Boon
Convolutional Neural Network (CNN) is the most popular method of deep learning in the machine learning field. Training a CNN has always been a demanding task compared to other machine learning paradigms, and this is due to its big space of hyper-parameters such as convolutional kernel size, number of strides, number of layers, pooling window size, etc. What makes the CNN’s huge hyper-parameters space optimization harder is that there is no universal robust theory supporting it, and any work flow proposed so far in literature is based on heuristics that are just rules of thumb and only depend on the dataset and problem at hand. In this work, it is empirically illustrated that the performance of a CNN is not linked only with the choice of the right hyper-parameters, but also linked to how some of the CNN operations are implemented. More specifically, the CNN performance is contrasted for two different implementations: cropping and padding the input volume. The results state that padding the input volume achieves higher accuracy and takes less time in training compared with cropping method.
{"title":"Either crop or pad the input volume: What is beneficial for Convolutional Neural Network?","authors":"U. M. Al-Saggaf, Abdelaziz Botalb, M. Moinuddin, S. Alfakeh, Syed Saad Azhar Ali, Tang Tong Boon","doi":"10.1109/ICIAS49414.2021.9642661","DOIUrl":"https://doi.org/10.1109/ICIAS49414.2021.9642661","url":null,"abstract":"Convolutional Neural Network (CNN) is the most popular method of deep learning in the machine learning field. Training a CNN has always been a demanding task compared to other machine learning paradigms, and this is due to its big space of hyper-parameters such as convolutional kernel size, number of strides, number of layers, pooling window size, etc. What makes the CNN’s huge hyper-parameters space optimization harder is that there is no universal robust theory supporting it, and any work flow proposed so far in literature is based on heuristics that are just rules of thumb and only depend on the dataset and problem at hand. In this work, it is empirically illustrated that the performance of a CNN is not linked only with the choice of the right hyper-parameters, but also linked to how some of the CNN operations are implemented. More specifically, the CNN performance is contrasted for two different implementations: cropping and padding the input volume. The results state that padding the input volume achieves higher accuracy and takes less time in training compared with cropping method.","PeriodicalId":212635,"journal":{"name":"2020 8th International Conference on Intelligent and Advanced Systems (ICIAS)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131072742","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 : 2021-07-13DOI: 10.1109/ICIAS49414.2021.9642576
Kean Wen Chua, G. S. Ng, S. Cheab, S. Soeung
In this paper, chained-response method is applied to the synthesis and design analysis of the substrate integrate waveguide (SIW) filters. SIW is smaller in size and offers low loss as well as high power handling just like the conventional waveguide filters. Chained-response multiband provides the flexibility in selecting inner-band frequency and the bandwidth for each of the passband. It is able to further improve the integration of wireless communication into a multiband system. From the simulation run in ANSYS HFSS, it is shown to have a good return loss performance of 13dB and an insertion loss of 1. 7dB, with a fractional bandwidth (FWB) of 3.5%. A good agreement between the theoretical value and simulated value can be seen.
{"title":"Synthesis of Chebyshev Function Substrate Integrated Waveguide Filter","authors":"Kean Wen Chua, G. S. Ng, S. Cheab, S. Soeung","doi":"10.1109/ICIAS49414.2021.9642576","DOIUrl":"https://doi.org/10.1109/ICIAS49414.2021.9642576","url":null,"abstract":"In this paper, chained-response method is applied to the synthesis and design analysis of the substrate integrate waveguide (SIW) filters. SIW is smaller in size and offers low loss as well as high power handling just like the conventional waveguide filters. Chained-response multiband provides the flexibility in selecting inner-band frequency and the bandwidth for each of the passband. It is able to further improve the integration of wireless communication into a multiband system. From the simulation run in ANSYS HFSS, it is shown to have a good return loss performance of 13dB and an insertion loss of 1. 7dB, with a fractional bandwidth (FWB) of 3.5%. A good agreement between the theoretical value and simulated value can be seen.","PeriodicalId":212635,"journal":{"name":"2020 8th International Conference on Intelligent and Advanced Systems (ICIAS)","volume":"81 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132175463","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 : 2021-07-13DOI: 10.1109/ICIAS49414.2021.9642695
Chung Yee Haw, A. Awang
In Wireless Sensor Network (WSN), ad hoc routing mechanisms assume location awareness of nodes by maintaining neighbourhood routing information frequently. Successive updates and distribution of routing tables result in transmission energy consumption not being optimized. To tackle this issue, cross-layer design is one of the effective techniques. However, before developing a cross-layer protocol, we focus on the performance evaluation of several routing protocols that will be used in the cross-layer design such as Ad Hoc On Demand Distance Vector (AODV), Optimized Link State Routing (OLSR), Dynamic Source Routing (DSR), and Zone Routing Protocol (ZRP). Their performances have been evaluated in terms of packet delivery ratio, average energy consumption per data packet, end-to-end delay and residual energy using NS2 simulator. Preliminary results have shown that ZRP protocol offers better overall performance and it is preferred in the cross-layer design. In this paper, we also propose an idea of T-IARP protocol which is a cross-layer design protocol based on Medium Access Control (MAC) and routing protocol. As for this proposed scheme, instead of exchanging the routing information among intermediate nodes, the control frames in MAC layer fully utilize the routing information from the network layer and reserve the selected nodes involved in the actual data transmission. The routing path is maintained by exchanging only the control frames. Exchanges of control frames incurs lesser overhead. Furthermore, the reserved nodes transmit data with adaptive wake-up/sleep duty cycle. However, the performance evaluation of this proposed protocol is planned as part of the future work in this research.
{"title":"A Performance Study on the Ad-hoc Routing Protocol Used in the Cross-Layer Design for Wireless Sensor Network","authors":"Chung Yee Haw, A. Awang","doi":"10.1109/ICIAS49414.2021.9642695","DOIUrl":"https://doi.org/10.1109/ICIAS49414.2021.9642695","url":null,"abstract":"In Wireless Sensor Network (WSN), ad hoc routing mechanisms assume location awareness of nodes by maintaining neighbourhood routing information frequently. Successive updates and distribution of routing tables result in transmission energy consumption not being optimized. To tackle this issue, cross-layer design is one of the effective techniques. However, before developing a cross-layer protocol, we focus on the performance evaluation of several routing protocols that will be used in the cross-layer design such as Ad Hoc On Demand Distance Vector (AODV), Optimized Link State Routing (OLSR), Dynamic Source Routing (DSR), and Zone Routing Protocol (ZRP). Their performances have been evaluated in terms of packet delivery ratio, average energy consumption per data packet, end-to-end delay and residual energy using NS2 simulator. Preliminary results have shown that ZRP protocol offers better overall performance and it is preferred in the cross-layer design. In this paper, we also propose an idea of T-IARP protocol which is a cross-layer design protocol based on Medium Access Control (MAC) and routing protocol. As for this proposed scheme, instead of exchanging the routing information among intermediate nodes, the control frames in MAC layer fully utilize the routing information from the network layer and reserve the selected nodes involved in the actual data transmission. The routing path is maintained by exchanging only the control frames. Exchanges of control frames incurs lesser overhead. Furthermore, the reserved nodes transmit data with adaptive wake-up/sleep duty cycle. However, the performance evaluation of this proposed protocol is planned as part of the future work in this research.","PeriodicalId":212635,"journal":{"name":"2020 8th International Conference on Intelligent and Advanced Systems (ICIAS)","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134407850","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 : 2021-07-13DOI: 10.1109/ICIAS49414.2021.9642676
K. Reddy, I. Elamvazuthi, A. Aziz, S. Paramasivam, Hui Na Chua
Cardiovascular diseases (CVDs) are killing about 17.9 million people every year. Early prediction can help people to change their lifestyles and to endure proper medical treatment if necessary. The data available in the healthcare sector is very useful to predict whether a patient will have a disease or not in the future. In this research, several machine learning algorithms such as Decision Tree (DT), Discriminant Analysis (DA), Logistic Regression (LR), Naïve Bayes (NB), Support Vector Machines (SVM), K-Nearest Neighbors (KNN), and Ensemble were trained on Cleveland heart disease dataset. The performance of the algorithms was evaluated using 10-fold cross-validation without and with Principal Component Analysis (PCA). LR provided the highest accuracy of 85.8% with PCA by keeping 9 components and Ensemble classifiers and attained an accuracy of 83.8% using a Bagged tree with PCA by keeping 10 components.
{"title":"Heart Disease Risk Prediction using Machine Learning with Principal Component Analysis","authors":"K. Reddy, I. Elamvazuthi, A. Aziz, S. Paramasivam, Hui Na Chua","doi":"10.1109/ICIAS49414.2021.9642676","DOIUrl":"https://doi.org/10.1109/ICIAS49414.2021.9642676","url":null,"abstract":"Cardiovascular diseases (CVDs) are killing about 17.9 million people every year. Early prediction can help people to change their lifestyles and to endure proper medical treatment if necessary. The data available in the healthcare sector is very useful to predict whether a patient will have a disease or not in the future. In this research, several machine learning algorithms such as Decision Tree (DT), Discriminant Analysis (DA), Logistic Regression (LR), Naïve Bayes (NB), Support Vector Machines (SVM), K-Nearest Neighbors (KNN), and Ensemble were trained on Cleveland heart disease dataset. The performance of the algorithms was evaluated using 10-fold cross-validation without and with Principal Component Analysis (PCA). LR provided the highest accuracy of 85.8% with PCA by keeping 9 components and Ensemble classifiers and attained an accuracy of 83.8% using a Bagged tree with PCA by keeping 10 components.","PeriodicalId":212635,"journal":{"name":"2020 8th International Conference on Intelligent and Advanced Systems (ICIAS)","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116108547","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 : 2021-07-13DOI: 10.1109/icias49414.2021.9642562
{"title":"[ICIAS 2021 Front cover]","authors":"","doi":"10.1109/icias49414.2021.9642562","DOIUrl":"https://doi.org/10.1109/icias49414.2021.9642562","url":null,"abstract":"","PeriodicalId":212635,"journal":{"name":"2020 8th International Conference on Intelligent and Advanced Systems (ICIAS)","volume":"23 7","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120868727","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 : 2021-07-13DOI: 10.1109/ICIAS49414.2021.9642408
A. S. R. Jaifani, M. Ahmad, M. S. M. Saheed
This research proposes the development of an energy harvesting device that generates electrical power to be applied specifically for the pipeline monitoring system. Issues with the limited power supply of the pipeline monitoring system will be resolved by the conversion of vibration or mechanical energy into electrical energy, allowing real-time monitoring that can intelligently monitor the integrity of the underground pipelines continuously. For the preliminary Finite Element Analysis (FEA) simulation, a model was designed using the COMSOL software and was then studied. Some of the critical studies for the FEA is to find out the trend of frequency response, load dependence and acceleration dependence from a model towards its effect on the output voltage and power. The simulation shows that the piezoelectric generator modelled was able to provide its peak voltage and output when operating at its optimal condition at vibrating acceleration of 1 g. From the studies, significant trends can be recorded and analysed to enhance further future designs that apply piezoelectricity to convert electrical energy from sources of kinetic energy.
{"title":"Preliminary FEA Simulation of Piezoelectric Generator for Pipeline Monitoring Sensor","authors":"A. S. R. Jaifani, M. Ahmad, M. S. M. Saheed","doi":"10.1109/ICIAS49414.2021.9642408","DOIUrl":"https://doi.org/10.1109/ICIAS49414.2021.9642408","url":null,"abstract":"This research proposes the development of an energy harvesting device that generates electrical power to be applied specifically for the pipeline monitoring system. Issues with the limited power supply of the pipeline monitoring system will be resolved by the conversion of vibration or mechanical energy into electrical energy, allowing real-time monitoring that can intelligently monitor the integrity of the underground pipelines continuously. For the preliminary Finite Element Analysis (FEA) simulation, a model was designed using the COMSOL software and was then studied. Some of the critical studies for the FEA is to find out the trend of frequency response, load dependence and acceleration dependence from a model towards its effect on the output voltage and power. The simulation shows that the piezoelectric generator modelled was able to provide its peak voltage and output when operating at its optimal condition at vibrating acceleration of 1 g. From the studies, significant trends can be recorded and analysed to enhance further future designs that apply piezoelectricity to convert electrical energy from sources of kinetic energy.","PeriodicalId":212635,"journal":{"name":"2020 8th International Conference on Intelligent and Advanced Systems (ICIAS)","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131269672","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：