Pub Date : 2020-09-27DOI: 10.1109/SCOReD50371.2020.9251029
Abdulrahman Ahmed Ghaleb Amer, S. Z. Sapuan, N. Nasimuddin
A microwave metasurface (MS) absorber for ISM band applications is proposed and studied. The proposed MS structure consists of two metallic layers separated by two dielectric FR4 materials with a thickness of 1.6 mm. An air gap with a thickness of 10 mm placed between the dielectric layers. The proposed MS absorber exhibits near-unity absorption and wider absorption bandwidth at an operating frequency of 2.4 GHz under normal incidence. For oblique incidence, it shows wider absorption bandwidth and an absorption value of more than 93% for different incident angles for TEM-mode and more than 93% at for TE mode. Moreover, a numerical analysis presented to explain the physical interpretation of the absorption mechanism in detail.
{"title":"Efficient Metasurface Absorber for 2.4 GHz ISM-Band Applications","authors":"Abdulrahman Ahmed Ghaleb Amer, S. Z. Sapuan, N. Nasimuddin","doi":"10.1109/SCOReD50371.2020.9251029","DOIUrl":"https://doi.org/10.1109/SCOReD50371.2020.9251029","url":null,"abstract":"A microwave metasurface (MS) absorber for ISM band applications is proposed and studied. The proposed MS structure consists of two metallic layers separated by two dielectric FR4 materials with a thickness of 1.6 mm. An air gap with a thickness of 10 mm placed between the dielectric layers. The proposed MS absorber exhibits near-unity absorption and wider absorption bandwidth at an operating frequency of 2.4 GHz under normal incidence. For oblique incidence, it shows wider absorption bandwidth and an absorption value of more than 93% for different incident angles for TEM-mode and more than 93% at for TE mode. Moreover, a numerical analysis presented to explain the physical interpretation of the absorption mechanism in detail.","PeriodicalId":142867,"journal":{"name":"2020 IEEE Student Conference on Research and Development (SCOReD)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-09-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132095815","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 : 2020-09-27DOI: 10.1109/SCOReD50371.2020.9250986
Nogol Memari, Saranaz Abdollahi, Mahdi Maghrouni Ganzagh, M. Moghbel
Diabetes is a serious medical condition and regular screening for diabetes is of great importance as treatment options are most effective in the early stages of diabetes. Digital imaging of retina is considered as a low-cost method for screening and could be used in conjunction with computer-based image processing techniques to automatically detect early signs of diabetes utilizing diabetes-related pathologies visible in retinal fundus images. This research proposes a novel computer-assisted diagnosis (CAD) system for assisting with the screening of the population as up to 50% of the affected population are not aware of having diabetes. Moreover, these screenings are often carried out by an optometrist who receives some training with the patients being referred to an ophthalmologist if they show symptoms. Having a computer-assisted diagnosis system assisting the optometrist during the screening can greatly increase the detection rate for patients with diabetes by providing a second opinion and highlighting any suspicious pathologies. For achieving the highest detection rate possible, a hybrid machine learning approach is proposed in this research by combining Deep Learning with the AdaBoost classifier. The proposed computer-assisted diagnosis system starts with the segmentation of the blood vessels. Then, microaneurysms and exudates are segmentation from the image. Statistical and regional features are then extracted utilizing first, second, and higher-order image features. A Deep Learning framework will be utilized for extracting additional statistical image descriptors as a Deep Learning has superior contextual analysis capabilities compared to other machine learning techniques. Finally, the most informative features are selected by a minimal-redundancy maximal-relevance feature selection approach with an AdaBoost classifier analyzing all the features and informing the operator regarding the patient’s condition. Ethereum Swarm blockchain-based decentralized cloud file storage provides the proposed CAD users with a secure storage olution to access the patient information and related images. The sensitivity, specificity, and accuracy of the classification will be measured under clinical conditions. Healthcare, government, and public users would receive the most benefit from this project.
{"title":"Computer-assisted diagnosis (CAD) system for Diabetic Retinopathy screening using color fundus images using Deep learning","authors":"Nogol Memari, Saranaz Abdollahi, Mahdi Maghrouni Ganzagh, M. Moghbel","doi":"10.1109/SCOReD50371.2020.9250986","DOIUrl":"https://doi.org/10.1109/SCOReD50371.2020.9250986","url":null,"abstract":"Diabetes is a serious medical condition and regular screening for diabetes is of great importance as treatment options are most effective in the early stages of diabetes. Digital imaging of retina is considered as a low-cost method for screening and could be used in conjunction with computer-based image processing techniques to automatically detect early signs of diabetes utilizing diabetes-related pathologies visible in retinal fundus images. This research proposes a novel computer-assisted diagnosis (CAD) system for assisting with the screening of the population as up to 50% of the affected population are not aware of having diabetes. Moreover, these screenings are often carried out by an optometrist who receives some training with the patients being referred to an ophthalmologist if they show symptoms. Having a computer-assisted diagnosis system assisting the optometrist during the screening can greatly increase the detection rate for patients with diabetes by providing a second opinion and highlighting any suspicious pathologies. For achieving the highest detection rate possible, a hybrid machine learning approach is proposed in this research by combining Deep Learning with the AdaBoost classifier. The proposed computer-assisted diagnosis system starts with the segmentation of the blood vessels. Then, microaneurysms and exudates are segmentation from the image. Statistical and regional features are then extracted utilizing first, second, and higher-order image features. A Deep Learning framework will be utilized for extracting additional statistical image descriptors as a Deep Learning has superior contextual analysis capabilities compared to other machine learning techniques. Finally, the most informative features are selected by a minimal-redundancy maximal-relevance feature selection approach with an AdaBoost classifier analyzing all the features and informing the operator regarding the patient’s condition. Ethereum Swarm blockchain-based decentralized cloud file storage provides the proposed CAD users with a secure storage olution to access the patient information and related images. The sensitivity, specificity, and accuracy of the classification will be measured under clinical conditions. Healthcare, government, and public users would receive the most benefit from this project.","PeriodicalId":142867,"journal":{"name":"2020 IEEE Student Conference on Research and Development (SCOReD)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-09-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133913622","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 : 2020-09-27DOI: 10.1109/SCOReD50371.2020.9250981
Izhar Izzudin bin Jamaludin, Hasliza Hassan
Serial Peripheral Interface (SPI) is a commonly used communication protocol that allows serial data transfer between a master and a slave device over a short distance. However, the current implementation of the Serial Peripheral Interface has a low speed and clock synchronization issue. When it comes to automotive, there a few things that are needed to be taken into consideration to increase the performance of the interface device. The paper present the design, simulation, verification and optimize SPI based on automotive interface device specifications. This includes a higher speed for the interface device and the efficiency of power dissipation. The SPI has been successfully optimized with a 1000MHz speed, a power of $575.7694 mu mathrm{W}$ and a total area of 1102.81mm2. The speed and area achieved are well improved over the current design of SPI. Even though the total dissipation achieved is above the current implemented SPI design, it is acceptable due to the technical relation between power and speed in VLSI design.
串行外设接口(SPI)是一种常用的通信协议，它允许在主设备和从设备之间进行短距离的串行数据传输。然而，目前串行外设接口的实现存在低速和时钟同步问题。当涉及到汽车，有一些事情需要考虑到提高接口设备的性能。本文介绍了基于汽车接口器件规范的SPI的设计、仿真、验证和优化。这包括更高的接口器件速度和功耗效率。该SPI已成功优化，速度为1000MHz，功耗为575.7694 mu mathm {W}$，总面积为1102.81mm2。实现的速度和面积都比目前的SPI设计有了很大的提高。尽管实现的总耗散高于目前实现的SPI设计，但由于VLSI设计中功率和速度之间的技术关系，它是可以接受的。
{"title":"Design and Analysis of Serial Peripheral Interface for Automotive Controller","authors":"Izhar Izzudin bin Jamaludin, Hasliza Hassan","doi":"10.1109/SCOReD50371.2020.9250981","DOIUrl":"https://doi.org/10.1109/SCOReD50371.2020.9250981","url":null,"abstract":"Serial Peripheral Interface (SPI) is a commonly used communication protocol that allows serial data transfer between a master and a slave device over a short distance. However, the current implementation of the Serial Peripheral Interface has a low speed and clock synchronization issue. When it comes to automotive, there a few things that are needed to be taken into consideration to increase the performance of the interface device. The paper present the design, simulation, verification and optimize SPI based on automotive interface device specifications. This includes a higher speed for the interface device and the efficiency of power dissipation. The SPI has been successfully optimized with a 1000MHz speed, a power of $575.7694 mu mathrm{W}$ and a total area of 1102.81mm2. The speed and area achieved are well improved over the current design of SPI. Even though the total dissipation achieved is above the current implemented SPI design, it is acceptable due to the technical relation between power and speed in VLSI design.","PeriodicalId":142867,"journal":{"name":"2020 IEEE Student Conference on Research and Development (SCOReD)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-09-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133945669","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 : 2020-09-27DOI: 10.1109/SCOReD50371.2020.9251024
D. Almeida, J. Pasupuleti, J. Ekanayake
The overvoltage issue has been deemed as a significant technical challenge owing to the high integration of solar photovoltaic (PV) systems into the low voltage (LV) distribution networks. As a promising solution to this problem, smart inverter controls have gained attention in facilitating localized voltage control. In this paper, the effectiveness of three smart inverter functionalities namely; Volt-Var, Volt-Watt, and simultaneous Volt-Var and Volt-Watt controls have been analyzed and quantified in terms of multiple performance criterion. A detailed analysis has been conducted using a generic, Malaysian LV distribution network in order to demonstrate the applicability of adopting smart inverter controls in alleviating overvoltage issues in PV-rich LV networks. Results reveal that the usage of smart inverter controls help to mitigate overvoltage issues and support network operation conditions. Further, the results highlight the importance of selecting the most suitable control technique for a better network performance.
{"title":"Assessing the Performance of Smart Inverter Functionalities in PV-Rich LV Distribution Networks","authors":"D. Almeida, J. Pasupuleti, J. Ekanayake","doi":"10.1109/SCOReD50371.2020.9251024","DOIUrl":"https://doi.org/10.1109/SCOReD50371.2020.9251024","url":null,"abstract":"The overvoltage issue has been deemed as a significant technical challenge owing to the high integration of solar photovoltaic (PV) systems into the low voltage (LV) distribution networks. As a promising solution to this problem, smart inverter controls have gained attention in facilitating localized voltage control. In this paper, the effectiveness of three smart inverter functionalities namely; Volt-Var, Volt-Watt, and simultaneous Volt-Var and Volt-Watt controls have been analyzed and quantified in terms of multiple performance criterion. A detailed analysis has been conducted using a generic, Malaysian LV distribution network in order to demonstrate the applicability of adopting smart inverter controls in alleviating overvoltage issues in PV-rich LV networks. Results reveal that the usage of smart inverter controls help to mitigate overvoltage issues and support network operation conditions. Further, the results highlight the importance of selecting the most suitable control technique for a better network performance.","PeriodicalId":142867,"journal":{"name":"2020 IEEE Student Conference on Research and Development (SCOReD)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-09-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"113996484","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}
Piezoelectric actuators are used in a wide range of applications, such as micropositioning stages, due to their high resolution and fast response. However, these actuators suffer from several nonlinearities that are mainly caused by hysteresis. This paper presents a hybrid control approach to overcome the hysteresis issue in such systems. A hysteresis-inversion-based feedforward controller is combined with a proportional– integral–derivative (PID) feedback controller, which is tuned using particle swarm optimization (PSO) to form the hybrid control structure. A new fitness that reduces the steady-state error, overshoot, and the rise and settling times is proposed. The proposed fitness function shows high efficiency and flexibility when used to tune the PID controller. The results show that the hybrid controller reduced the error caused by the hysteresis from 10.501% to 0.050% of the displacement range, producing a linear relationship between the input voltage and output displacement. The findings of this work prove that the hybrid control method can be potentially used in precise micropositioning and high precision applications.
{"title":"Hybrid Hysteresis-Inversion and PSO-Tuned PID Control for Piezoelectric Micropositioning Stages","authors":"Shadir Ahamed Mohamed Rifai, Marwan Nafea, Sanjoy Kumar Debnath, Susama Bagchi","doi":"10.1109/SCOReD50371.2020.9251012","DOIUrl":"https://doi.org/10.1109/SCOReD50371.2020.9251012","url":null,"abstract":"Piezoelectric actuators are used in a wide range of applications, such as micropositioning stages, due to their high resolution and fast response. However, these actuators suffer from several nonlinearities that are mainly caused by hysteresis. This paper presents a hybrid control approach to overcome the hysteresis issue in such systems. A hysteresis-inversion-based feedforward controller is combined with a proportional– integral–derivative (PID) feedback controller, which is tuned using particle swarm optimization (PSO) to form the hybrid control structure. A new fitness that reduces the steady-state error, overshoot, and the rise and settling times is proposed. The proposed fitness function shows high efficiency and flexibility when used to tune the PID controller. The results show that the hybrid controller reduced the error caused by the hysteresis from 10.501% to 0.050% of the displacement range, producing a linear relationship between the input voltage and output displacement. The findings of this work prove that the hybrid control method can be potentially used in precise micropositioning and high precision applications.","PeriodicalId":142867,"journal":{"name":"2020 IEEE Student Conference on Research and Development (SCOReD)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-09-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127686212","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 : 2020-09-27DOI: 10.1109/SCOReD50371.2020.9250972
Faizan Qamar, M. N. Hindia, T. A. Rahman, R. Hassan, S. Saleem
The millimeter wave (mmWave) frequency spectrum is being considered as the most promising communication systems to fulfill the bandwidth requirements for the next-generation wireless network. However, the mmWave frequency band has encountered several issues like fading, scattering, atmospheric absorption, and penetration losses as compared to the currently using frequency spectrum, which is under 6 GHz. Therefore, optimizing the propagation channel path at the mmWave band is seemed to be the only solution, which can help the operators to distinguish the signal behavior before practically implement the 5G networks. In this regard, this study aims to analyze the propagation characteristics for 26 GHz frequency band for the outdoor Single Side Parking (SSP) and Double Side Parking (DSP) environment. It utilizes the most potential propagation path loss models i.e., Close-In (CI) and Floating Intercept (FI). The results prove that the CI model can produce better results and delivers higher network performance as compared to the FI model.
{"title":"Outdoor Propagation Channel Investigation at 26 GHz for 5G mmWave Communication","authors":"Faizan Qamar, M. N. Hindia, T. A. Rahman, R. Hassan, S. Saleem","doi":"10.1109/SCOReD50371.2020.9250972","DOIUrl":"https://doi.org/10.1109/SCOReD50371.2020.9250972","url":null,"abstract":"The millimeter wave (mmWave) frequency spectrum is being considered as the most promising communication systems to fulfill the bandwidth requirements for the next-generation wireless network. However, the mmWave frequency band has encountered several issues like fading, scattering, atmospheric absorption, and penetration losses as compared to the currently using frequency spectrum, which is under 6 GHz. Therefore, optimizing the propagation channel path at the mmWave band is seemed to be the only solution, which can help the operators to distinguish the signal behavior before practically implement the 5G networks. In this regard, this study aims to analyze the propagation characteristics for 26 GHz frequency band for the outdoor Single Side Parking (SSP) and Double Side Parking (DSP) environment. It utilizes the most potential propagation path loss models i.e., Close-In (CI) and Floating Intercept (FI). The results prove that the CI model can produce better results and delivers higher network performance as compared to the FI model.","PeriodicalId":142867,"journal":{"name":"2020 IEEE Student Conference on Research and Development (SCOReD)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-09-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115234008","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 : 2020-09-27DOI: 10.1109/SCOReD50371.2020.9251009
R. M. Tawafak, Ghaliya Alfarsi, S. I. Malik, Abdalla Eldow, J. Jabbar, Abir AlSideiri
Cancer is caused by damage to the genes that control cell growth and division. however, still many applications try to Detection/diagnosis/treatment is possible using application software. By confirming cell growth and treatment by correcting the mechanism of gene damage or by stopping the blood Supplying cells or by destroying them. this study tries to answer the question: How to prove a possible disease outbreak? the literature review investigated the Analysis of requirements involved in the design and development of FBP. The method develops a simple software, divided into multi phases as an alternative to regular clinical visits. The main requirements of this application cover Concepts and terms of clinic needs match with patient disease level. the software results show the satisfaction of patients who uses the software for the early process of generating information through the User interface, to reduce any distrust or concerns.
{"title":"Cancer Treatment Disease Application Software Technology in Medicine","authors":"R. M. Tawafak, Ghaliya Alfarsi, S. I. Malik, Abdalla Eldow, J. Jabbar, Abir AlSideiri","doi":"10.1109/SCOReD50371.2020.9251009","DOIUrl":"https://doi.org/10.1109/SCOReD50371.2020.9251009","url":null,"abstract":"Cancer is caused by damage to the genes that control cell growth and division. however, still many applications try to Detection/diagnosis/treatment is possible using application software. By confirming cell growth and treatment by correcting the mechanism of gene damage or by stopping the blood Supplying cells or by destroying them. this study tries to answer the question: How to prove a possible disease outbreak? the literature review investigated the Analysis of requirements involved in the design and development of FBP. The method develops a simple software, divided into multi phases as an alternative to regular clinical visits. The main requirements of this application cover Concepts and terms of clinic needs match with patient disease level. the software results show the satisfaction of patients who uses the software for the early process of generating information through the User interface, to reduce any distrust or concerns.","PeriodicalId":142867,"journal":{"name":"2020 IEEE Student Conference on Research and Development (SCOReD)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-09-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125799593","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 : 2020-09-27DOI: 10.1109/SCOReD50371.2020.9250939
Susama Bagchi, M. N. Mohd, Sanjoy Kumar Debnath, Marwan Nafea, N. S. Suriani, Yoosuf Nizam
The false-positive breast cancer cases detected by radiologists and Computer-aided Detection (CAD) systems increase the medical cost and patient discomfort due to the unnecessary breast biopsies. These available CAD systems were developed using traditional machine learning techniques for breast cancer diagnosis. A noteworthy progress is happening in cancer diagnosis after the introduction of deep learning in Convolutional Neural Networks (CNNs) for CAD development. This paper compares the performance of three pre-trained Residual Networks (ResNets), i.e., ResNet18, ResNet50, and ResNet101 with increased image input layer size of $512times 512times 3$ for the classification of the pre-processed whole mammograms into normal, benign, and malignant categories. INbreast dataset was pre-processed and then these pre-processed whole breast images were segregated into three categories based on the ground truths. Original and modified networks were developed by replacing the last three layers of the selected ResNets to match the output category along with the image input layer. Data augmentation and transfer learning were applied to overcome the overfitting issue due to smaller dataset. The developed models were tested and the attained training and testing accuracies, sensitivity, and specificity were compared to evaluate their performances. It was observed that ResNet50 with an image input layer of size $512times 512times 3$ provided best results after five-fold training and the test accuracy was 79.27% with the average sensitivity and specificity of 0.76, and 0.89, respectively for three categories. This experimental work is significant as it proves that the increased image input layer size has a considerable effect in classifying the whole mammograms. Further development will be done with a balanced dataset and other pre-trained deep networks will also be tried.
{"title":"Performance Comparison of Pre-trained Residual Networks for Classification of the Whole Mammograms with Smaller Dataset","authors":"Susama Bagchi, M. N. Mohd, Sanjoy Kumar Debnath, Marwan Nafea, N. S. Suriani, Yoosuf Nizam","doi":"10.1109/SCOReD50371.2020.9250939","DOIUrl":"https://doi.org/10.1109/SCOReD50371.2020.9250939","url":null,"abstract":"The false-positive breast cancer cases detected by radiologists and Computer-aided Detection (CAD) systems increase the medical cost and patient discomfort due to the unnecessary breast biopsies. These available CAD systems were developed using traditional machine learning techniques for breast cancer diagnosis. A noteworthy progress is happening in cancer diagnosis after the introduction of deep learning in Convolutional Neural Networks (CNNs) for CAD development. This paper compares the performance of three pre-trained Residual Networks (ResNets), i.e., ResNet18, ResNet50, and ResNet101 with increased image input layer size of $512times 512times 3$ for the classification of the pre-processed whole mammograms into normal, benign, and malignant categories. INbreast dataset was pre-processed and then these pre-processed whole breast images were segregated into three categories based on the ground truths. Original and modified networks were developed by replacing the last three layers of the selected ResNets to match the output category along with the image input layer. Data augmentation and transfer learning were applied to overcome the overfitting issue due to smaller dataset. The developed models were tested and the attained training and testing accuracies, sensitivity, and specificity were compared to evaluate their performances. It was observed that ResNet50 with an image input layer of size $512times 512times 3$ provided best results after five-fold training and the test accuracy was 79.27% with the average sensitivity and specificity of 0.76, and 0.89, respectively for three categories. This experimental work is significant as it proves that the increased image input layer size has a considerable effect in classifying the whole mammograms. Further development will be done with a balanced dataset and other pre-trained deep networks will also be tried.","PeriodicalId":142867,"journal":{"name":"2020 IEEE Student Conference on Research and Development (SCOReD)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-09-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127482988","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 : 2020-09-27DOI: 10.1109/SCOReD50371.2020.9250934
A. Ayub, M. Othman, Nan M. Sahar, M. Azni, M. A. Ilyas, M. Jaafar
Augmented Reality (AR) is one of the technologies that has increased popularity in industry revolution 4.0 (IR 4.0). This technology is widely used in the education sector that can help the students easily acquire, process, and remember the information. However, due to the lack of introduction to new technology in some education fields, primary students tend to only use conventional learning methods such as books or card games. By looking at this loophole, this project is focusing on the primary students that being called remedial students in Remedial Education Program (RP). We choose the consonant vowel consonant (KVK) module after a deep discussion with the remedial teacher and regional education officer in Batu Pahat. The record shows that remedial students are facing hardship to spell, read, and pronounce the KVK. We have successfully developed the AR application education platform apps by using the Unity Real-Time Development platform (Unity 3D) and Vuforia. Inside this application, there are two menus for learning purposes which are KVK and Suku Kata and one menu for evaluation which is Kuiz. This module has been tested to 25 remedial students and the results show that the evaluation time taken to answer the Kuiz from the apps has been reduced around 10% to 50% compared to the conventional method. We hope that this application can be applied widely for remedial students in elementary school in year one that has a problem in mastering the KVK for REP.
增强现实(AR)是在工业革命4.0 (IR 4.0)中越来越受欢迎的技术之一。该技术广泛应用于教育领域，可以帮助学生方便地获取、处理和记忆信息。然而，由于在一些教育领域缺乏对新技术的介绍，小学生往往只使用传统的学习方法，如书籍或纸牌游戏。通过寻找这个漏洞，该项目将重点放在了在补习教育计划(RP)中被称为补习学生的小学生身上。在与Batu Pahat的补习老师和区域教育官员深入讨论后，我们选择了辅音元音辅音(KVK)模块。记录显示，补习学生在拼写、阅读和发音KVK方面面临困难。我们利用Unity实时开发平台(Unity 3D)和Vuforia成功开发了AR应用教育平台app。在这个应用程序中，有两个用于学习的菜单，分别是KVK和Suku Kata，还有一个用于评估的菜单，即Kuiz。该模块已在25名补习学生中进行了测试，结果表明，与传统方法相比，从应用程序中回答Kuiz所需的评估时间减少了约10%至50%。我们希望这个应用程序可以广泛应用于小学一年级对REP的KVK掌握有问题的补习学生。
{"title":"Learning Tools of KVK Module using Augmented Reality Mobile Application for Remedial Education Program (REP)","authors":"A. Ayub, M. Othman, Nan M. Sahar, M. Azni, M. A. Ilyas, M. Jaafar","doi":"10.1109/SCOReD50371.2020.9250934","DOIUrl":"https://doi.org/10.1109/SCOReD50371.2020.9250934","url":null,"abstract":"Augmented Reality (AR) is one of the technologies that has increased popularity in industry revolution 4.0 (IR 4.0). This technology is widely used in the education sector that can help the students easily acquire, process, and remember the information. However, due to the lack of introduction to new technology in some education fields, primary students tend to only use conventional learning methods such as books or card games. By looking at this loophole, this project is focusing on the primary students that being called remedial students in Remedial Education Program (RP). We choose the consonant vowel consonant (KVK) module after a deep discussion with the remedial teacher and regional education officer in Batu Pahat. The record shows that remedial students are facing hardship to spell, read, and pronounce the KVK. We have successfully developed the AR application education platform apps by using the Unity Real-Time Development platform (Unity 3D) and Vuforia. Inside this application, there are two menus for learning purposes which are KVK and Suku Kata and one menu for evaluation which is Kuiz. This module has been tested to 25 remedial students and the results show that the evaluation time taken to answer the Kuiz from the apps has been reduced around 10% to 50% compared to the conventional method. We hope that this application can be applied widely for remedial students in elementary school in year one that has a problem in mastering the KVK for REP.","PeriodicalId":142867,"journal":{"name":"2020 IEEE Student Conference on Research and Development (SCOReD)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-09-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125556530","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 : 2020-09-27DOI: 10.1109/SCOReD50371.2020.9251003
H. Ithnin, E. J. Mohamad, N. H. Yusoff, N. M. Lip
At present, demands for measurement in industrial process control is advancing to another level, from one-dimension profiling to two- and three-dimension imaging technique. These advancements empowered and assisted in providing more information on the ongoing processes. For industrial process flow study, Single Photon Emission Computed Tomography (SPECT) system, can produce a cross-sectional image of the radioactive source distribution inside a vessel or pipeline. However, an optimum number of measurements is required to reconstruct the cross-section image without compromising or reducing the information on the reconstructed image. In this study, a time average emission computed tomography system was set up and utilised for mapping the intensity of the gamma-ray radiation from a static Barium, Ba-133 isotropic sealed source. The gamma-ray radiation source was placed on the centre and off-centre of the scanning region. Sodium Iodide, NaI scintillation detector then measure the intensity of the gamma-ray (emitted from the radioactive source) at a different angle. The data of gamma-ray intensity distribution were analysed, and the tomographic image of it was reconstructed using the Filtered Back Projection (FBP) algorithm. Although the SPECT system used is a time-average measurement, the tomographic image result is useful for the development of real-time industrial SPECT system that will be used for the imaging system in industrial process control.
{"title":"An Experimental Gamma-ray Emission Computed Tomography System for Intensity Mapping of An Isotropic Sealed Source","authors":"H. Ithnin, E. J. Mohamad, N. H. Yusoff, N. M. Lip","doi":"10.1109/SCOReD50371.2020.9251003","DOIUrl":"https://doi.org/10.1109/SCOReD50371.2020.9251003","url":null,"abstract":"At present, demands for measurement in industrial process control is advancing to another level, from one-dimension profiling to two- and three-dimension imaging technique. These advancements empowered and assisted in providing more information on the ongoing processes. For industrial process flow study, Single Photon Emission Computed Tomography (SPECT) system, can produce a cross-sectional image of the radioactive source distribution inside a vessel or pipeline. However, an optimum number of measurements is required to reconstruct the cross-section image without compromising or reducing the information on the reconstructed image. In this study, a time average emission computed tomography system was set up and utilised for mapping the intensity of the gamma-ray radiation from a static Barium, Ba-133 isotropic sealed source. The gamma-ray radiation source was placed on the centre and off-centre of the scanning region. Sodium Iodide, NaI scintillation detector then measure the intensity of the gamma-ray (emitted from the radioactive source) at a different angle. The data of gamma-ray intensity distribution were analysed, and the tomographic image of it was reconstructed using the Filtered Back Projection (FBP) algorithm. Although the SPECT system used is a time-average measurement, the tomographic image result is useful for the development of real-time industrial SPECT system that will be used for the imaging system in industrial process control.","PeriodicalId":142867,"journal":{"name":"2020 IEEE Student Conference on Research and Development (SCOReD)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-09-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131224800","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：