2021 11th IEEE International Conference on Control System, Computing and Engineering (ICCSCE)最新文献_第2页

High-level Features in Deeper Deep Learning Layers for Breast Cancer Classification 用于乳腺癌分类的深层深度学习层的高级特征

2021 11th IEEE International Conference on Control System, Computing and Engineering (ICCSCE) Pub Date : 2021-08-27 DOI: 10.1109/ICCSCE52189.2021.9530911

Noorma Razali, I. Isa, S. N. Sulaiman, N. Karim, M. K. Osman

{"title":"High-level Features in Deeper Deep Learning Layers for Breast Cancer Classification","authors":"Noorma Razali, I. Isa, S. N. Sulaiman, N. Karim, M. K. Osman","doi":"10.1109/ICCSCE52189.2021.9530911","DOIUrl":"https://doi.org/10.1109/ICCSCE52189.2021.9530911","url":null,"abstract":"Early detection of breast cancer is crucial when treating than cure in later mammogram screening processes. To date, researchers extensively proposed the implementation of artificial intelligence to develop a computer-aided system (CAD) to determine types of breast tumour lesion, whether benign or malignant. This approach is significant to minimise the rate of misinterpretation in false positive and false negative diagnosis results among radiologists. Lack of established medical datasets publicly available has become the main reason why the system is not fully implemented in clinical settings yet. This study is aimed to investigate the performance of a convolutional neural network (CNN) to detect cancerous lesion types. The pre-trained CNN networks are tested on two established public datasets, CBIS-DDSM and INbreast. Pre-processing using denoising and contrast limited adaptive histogram equalisation (CLAHE) and augmented to lessen the effect of overfitting. The pre-trained CNNs AlexNet and InceptionV3 represent shallow and deeper neural networks respectively, trained using the transfer learning method. Performance of the system is tested and its accuracy, losses, sensitivity, specificity, and receiver operating characteristic curve (ROC) are evaluated. The InceptionV3 network performs better with the highest testing and area under the curve (AUC) at 99.93% compared to shallower AlexNet at 98.92% using INbreast dataset. Training the system using augmented data is proven to improve testing accuracy at 86.7% from 60.26% using a non-augmented dataset in low-quality input images. Meanwhile, using a shallower network for transfer learning produces high accuracy results without compromising computational cost. This study serves as the platform to improve the system’s performance by varying the pretrained networks used and getting different features from each convolutional layer to be trained in the future.","PeriodicalId":285507,"journal":{"name":"2021 11th IEEE International Conference on Control System, Computing and Engineering (ICCSCE)","volume":"65 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-08-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133769845","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}

引用次数: 3

Second Order Sliding Mode Controller for Altitude and Yaw Control of Quadcopter 四轴飞行器高度和偏航控制的二阶滑模控制器

2021 11th IEEE International Conference on Control System, Computing and Engineering (ICCSCE) Pub Date : 2021-08-27 DOI: 10.1109/ICCSCE52189.2021.9530850

T. H. Chiew, Hao-Ern Lee, Y. Lee, K. Chang, Jia Jan Ong, K. Eu

{"title":"Second Order Sliding Mode Controller for Altitude and Yaw Control of Quadcopter","authors":"T. H. Chiew, Hao-Ern Lee, Y. Lee, K. Chang, Jia Jan Ong, K. Eu","doi":"10.1109/ICCSCE52189.2021.9530850","DOIUrl":"https://doi.org/10.1109/ICCSCE52189.2021.9530850","url":null,"abstract":"Unmanned aerial vehicles are very attractive to industrial practitioners due to their high maneuverability and ability to perform vertical take-off landing. The accuracy in altitude and yaw movement control become vital for vertical take-off landing. This paper examines and compares the ability of a second order sliding mode controller in altitude and yaw tracking control of a quadcopter against the traditional proportional-derivative controller. Both controllers were designed and numerically analyzed on a mathematical model of a quadcopter. Two types of input were generated, namely; slow-rate input in which only one set point was set, and fast-rate input in which more than one set point was set. Both inputs were injected into the system respectively and both controllers were evaluated and compared in terms of maximum overshoot, settling time and root-mean-square tracking error. Simulation results showed that second order sliding mode controller outperformed traditional linear controller in all considered performance indicators for both hovering and yaw motion control. A reduction of more than 80% has been achieved in terms of maximum overshoot. The chattering effect was reduced by using logistic function. The effectiveness of this controller would promote its application in real-time due to its great control performances compared to standard controller.","PeriodicalId":285507,"journal":{"name":"2021 11th IEEE International Conference on Control System, Computing and Engineering (ICCSCE)","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-08-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114300083","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}

引用次数: 1

Arabic Vehicle Licence Plate Recognition Using Deep Learning Methods: Review 阿拉伯车牌识别使用深度学习方法:回顾

2021 11th IEEE International Conference on Control System, Computing and Engineering (ICCSCE) Pub Date : 2021-08-27 DOI: 10.1109/ICCSCE52189.2021.9530940

G. Alkawsi, Yahia Baashar, A. Alkahtani, S. Tiong, Dhuha Habeeb, Ammar Aliubari

{"title":"Arabic Vehicle Licence Plate Recognition Using Deep Learning Methods: Review","authors":"G. Alkawsi, Yahia Baashar, A. Alkahtani, S. Tiong, Dhuha Habeeb, Ammar Aliubari","doi":"10.1109/ICCSCE52189.2021.9530940","DOIUrl":"https://doi.org/10.1109/ICCSCE52189.2021.9530940","url":null,"abstract":"Automatic vehicle identification via its license plate is proven to be a valuable solution for smart transportation and smart city applications. The most recent studies explore the implementation of deep learning techniques to improve the license plate recognition performance concerning the challenges and difficulties associated with license plates, such as languages, fonts, distortions, hazardous situations, and blurriness and illumination diversions. In many Middle East countries, vehicle plates include letters, numbers, and city names written in Arabic. Many deep learning approaches have been conducted to improve identification accuracy, with many performance issues. This study reviews the current deep learning methods used in the automatic identification system of such license plates, focusing on the process of deduction, segmentation, and recognition. Methods were analyzed and compared based on applied attributes, strengths, weaknesses, and recognition performance. The paper aims to highlight the research gaps in this area and give some insights into filling them by providing all the related information and proposing new ideas to develop the research further.","PeriodicalId":285507,"journal":{"name":"2021 11th IEEE International Conference on Control System, Computing and Engineering (ICCSCE)","volume":"86 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-08-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123123117","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}

引用次数: 2

Design and Development of GMapping based SLAM Algorithm in Virtual Agricultural Environment 虚拟农业环境中基于GMapping的SLAM算法设计与开发

2021 11th IEEE International Conference on Control System, Computing and Engineering (ICCSCE) Pub Date : 2021-08-27 DOI: 10.1109/ICCSCE52189.2021.9530991

M. Ratul, M. S. A. Mahmud, M. Abidin, R. Ayop

{"title":"Design and Development of GMapping based SLAM Algorithm in Virtual Agricultural Environment","authors":"M. Ratul, M. S. A. Mahmud, M. Abidin, R. Ayop","doi":"10.1109/ICCSCE52189.2021.9530991","DOIUrl":"https://doi.org/10.1109/ICCSCE52189.2021.9530991","url":null,"abstract":"The global population’s continuous growth has speeded up the search for an efficient ways of crop production. More significant environmental and food safety considerations are pushing farmers to track and incorporate inputs reliably. The latest technology and research results are increasingly used in agriculture, especially in intensive cultures that ensure remunerative returns. This paper aims to design, simulate, verify, analyze, and develop an agricultural robot localization system in the greenhouse environment using GMapping algorithm-based SLAM approach. A simulation is conducted with an agricultural mobile robot (Turtlebot3) using GMapping algorithm-based Simultaneous Localization and Mapping (SLAM) approach for autonomous navigation and continuous data collection. By using this approach, Turtlebot3 can roam around the environment while generating a map of the environment. Besides that, continuous data from a greenhouse environment can be obtained in which can significantly improve the autonomous agricultural environment farming performance.","PeriodicalId":285507,"journal":{"name":"2021 11th IEEE International Conference on Control System, Computing and Engineering (ICCSCE)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-08-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125425455","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}

引用次数: 7

Characterization of Backing Layer Piezoelectric Ultrasonic Transducers for Underwater Communication 水下通信衬底层压电超声换能器的特性研究

2021 11th IEEE International Conference on Control System, Computing and Engineering (ICCSCE) Pub Date : 2021-08-27 DOI: 10.1109/ICCSCE52189.2021.9530893

M. Subki, K. A. Ahmad, M. K. Osman, R. Boudville, S. Yahya, Mohamad Faizal Abd Rahman, Z. Hussain

{"title":"Characterization of Backing Layer Piezoelectric Ultrasonic Transducers for Underwater Communication","authors":"M. Subki, K. A. Ahmad, M. K. Osman, R. Boudville, S. Yahya, Mohamad Faizal Abd Rahman, Z. Hussain","doi":"10.1109/ICCSCE52189.2021.9530893","DOIUrl":"https://doi.org/10.1109/ICCSCE52189.2021.9530893","url":null,"abstract":"Underwater ultrasonic communication is a methods of sending and receiving messages for underwater level. Nowadays there is a lot application that have been discovered for example telecommunication between submarines There are several ways to communicate underwater level but the most common communication using hydrophone. Hydrophone can be build based on sensing element using piezoelectric material or capacitive material. Currently hydrophones based piezoelectric material are low sensitivity and narrow bandwidth. This will affect the sonar application when used the low performance of hydrophones. This project is aimed to design, simulate and characterize a new backing layer structure for piezoelectric ultrasonic transducer applied in underwater communication using finite element analysis (FEA). The study was included a different types of backing layers that applied for a new structure backing layer. There were 3 types of backing layer constructed, namely wood (pine), plastic (acrylic) and metal (titanium). The frequency ranges of 1 kHz to 100 kHz were applied in simulation. Piezoelectric ultrasonic transducer with titanium 21S metal has wide bandwidth of 53.7 %. The transmitting voltage response of the device was 110 dB rel 1 μPa/V. The material of titanium 21S metal has improved transducer performance where it was the highest performance between other materials.","PeriodicalId":285507,"journal":{"name":"2021 11th IEEE International Conference on Control System, Computing and Engineering (ICCSCE)","volume":"48 5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-08-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130865872","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}

引用次数: 0

Economic Dispatch of Micro-grid Considering Electric Vehicles 考虑电动汽车的微电网经济调度

2021 11th IEEE International Conference on Control System, Computing and Engineering (ICCSCE) Pub Date : 2021-08-27 DOI: 10.1109/ICCSCE52189.2021.9530948

Sim Wai Sheng, Sook Yee Yip, W. Raymond, K. Mei

引用次数: 1

Transient Stability Improvement of Power System using Power System Stabilizer Integrated with Excitation System 利用电力系统稳定器与励磁系统集成提高电力系统暂态稳定性

2021 11th IEEE International Conference on Control System, Computing and Engineering (ICCSCE) Pub Date : 2021-08-27 DOI: 10.1109/ICCSCE52189.2021.9530970

A. Alsakati, C. Vaithilingam, J. Alnasseir, A. Jagadeeshwaran

引用次数: 3

Road Image Segmentation using Unmanned Aerial Vehicle Images and DeepLab V3+ Semantic Segmentation Model 基于无人机图像和DeepLab V3+语义分割模型的道路图像分割

2021 11th IEEE International Conference on Control System, Computing and Engineering (ICCSCE) Pub Date : 2021-08-27 DOI: 10.1109/ICCSCE52189.2021.9530950

Mat Nizam Mahmud, M. K. Osman, A. P. Ismail, F. Ahmad, K. A. Ahmad, A. Ibrahim

{"title":"Road Image Segmentation using Unmanned Aerial Vehicle Images and DeepLab V3+ Semantic Segmentation Model","authors":"Mat Nizam Mahmud, M. K. Osman, A. P. Ismail, F. Ahmad, K. A. Ahmad, A. Ibrahim","doi":"10.1109/ICCSCE52189.2021.9530950","DOIUrl":"https://doi.org/10.1109/ICCSCE52189.2021.9530950","url":null,"abstract":"Road image segmentation is critical in a variety of applications, including road maintenance, intelligent transportation systems, and urban planning. Numerous image segmentation techniques, including popular neural network approaches, have been proposed for unmanned aerial vehicle (UAV) images recently. However, since these images include complex backgrounds, high-precision road segmentation from UAV images remains challenging. To address this issue, this study proposes a deep learning method called DeepLab V3+ semantic segmentation. Road images are captured and collected from several roads in Kedah and Selangor, Malaysia using a UAV. To segment the road from the background, the DeepLab V3+ with Resnet-50 backbone is utilised. Then, the performance is assessed by comparing segmented images by deep learning to manually segment images. Three metrics are used for the assessment; pixel accuracy (PA), mean area intersection by union (mIoU), and mean F1-score (MeanF1). The study also compares the segmentation performance with the DeepLab V3+ with mobile NetV2 for benchmarking purposes. Simulation results show that the DeepLab V3+ with Resnet-50 has performed better than the DeepLab V3+ with mobile NetV2 methods. The findings indicate that the DeepLab V3+ with Resnet-50 outperformed the DeepLab V3+ with mobile NetV2 for PA, mIoU, and MeanF1 by 1.39 %, 4.92 %, and 9.71 %, respectively.","PeriodicalId":285507,"journal":{"name":"2021 11th IEEE International Conference on Control System, Computing and Engineering (ICCSCE)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-08-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123921845","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}

引用次数: 6

Underwater Animal Detection Using YOLOV4 利用YOLOV4进行水下动物探测

2021 11th IEEE International Conference on Control System, Computing and Engineering (ICCSCE) Pub Date : 2021-08-27 DOI: 10.1109/ICCSCE52189.2021.9530877

Mohamed Rosli, I. Isa, M. Maruzuki, S. N. Sulaiman, Ibrahim Ahmad

{"title":"Underwater Animal Detection Using YOLOV4","authors":"Mohamed Rosli, I. Isa, M. Maruzuki, S. N. Sulaiman, Ibrahim Ahmad","doi":"10.1109/ICCSCE52189.2021.9530877","DOIUrl":"https://doi.org/10.1109/ICCSCE52189.2021.9530877","url":null,"abstract":"Underwater computer vision system has been widely used for many underwater applications such as ocean exploration, biological research and monitoring underwater life sustainability. However, in counterpart of the underwater environment, there are several challenges arise such as water murkiness, dynamic background, low light and low visibility which limits the ability to explore this area. To overcome these challenges, there is a crucial to improve underwater vision system that able to efficiently adapt with varying environments. Therefore, it is great of significance to propose an efficient and precise underwater detection by using YOLOv4 based on deep learning algorithm. In the research, an open-source underwater dataset was used to investigate YOLOv4 performance based on metrics evaluation of precision and processing speed (FPS). The result shows that YOLOv4 able to achieve a remarkable of 97.96% for mean average precision with frame per second of 46.6. This study shows that YOLOv4 model is highly significant to be implemented in underwater vision system as it possesses ability to accurately detect underwater objects with haze and low-light environments.","PeriodicalId":285507,"journal":{"name":"2021 11th IEEE International Conference on Control System, Computing and Engineering (ICCSCE)","volume":"58 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-08-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129287174","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}

引用次数: 9

[ICCSCE 2021 Front cover] [ic欧安会2021年封面]

2021 11th IEEE International Conference on Control System, Computing and Engineering (ICCSCE) Pub Date : 2021-08-27 DOI: 10.1109/iccsce52189.2021.9530999

引用次数: 0