发布求助
文献互助 智能选刊 最新文献

2021 International Conference on Digital Futures and Transformative Technologies (ICoDT2)最新文献

筛选
英文 中文
Performance Analysis of Deep Learning Frameworks for COVID 19 Detection 深度学习框架在COVID - 19检测中的性能分析
2021 International Conference on Digital Futures and Transformative Technologies (ICoDT2) Pub Date : 2021-05-20 DOI: 10.1109/ICoDT252288.2021.9441537
Muhammad Hassan Naviwala, Rizwan Qureshi
{"title":"Performance Analysis of Deep Learning Frameworks for COVID 19 Detection","authors":"Muhammad Hassan Naviwala, Rizwan Qureshi","doi":"10.1109/ICoDT252288.2021.9441537","DOIUrl":"https://doi.org/10.1109/ICoDT252288.2021.9441537","url":null,"abstract":"The Coronavirus known as COVID-19 is one of the biggest pandemic in the human history. About 3.12 million deaths and more than 150 million cases have been diagnosed to date. The economic cost of the virus is also huge, due to lockdown in many parts of the world. The traditional method to detect COVID-19 is a PCR test, but it takes about 4–5 hours to get the results. Secondly, in some cases, the false-negative ratio is high in PCR kits. As an alternative method, radiology images, like CT-scan and chest X-rays, can be used for COVID-19 diagnosis. Deep learning has shown remarkable results in medical image analysis, such as tumor segmentation. This paper evaluates four famous CNN models, VGG-16, AlexNet, ResNet18, and Inception V3, on the dataset complied with the chest X-ray images for COVID-19 patient. The models are trained on two public datasets. The simulation results show the effectiveness of deep learning models for COVID-19 detection.","PeriodicalId":207832,"journal":{"name":"2021 International Conference on Digital Futures and Transformative Technologies (ICoDT2)","volume":"241 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-05-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134243426","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
From Transformers to Reformers 从变形金刚到改革者
2021 International Conference on Digital Futures and Transformative Technologies (ICoDT2) Pub Date : 2021-05-20 DOI: 10.1109/ICoDT252288.2021.9441516
Nauman Riaz, Seemab Latif, R. Latif
{"title":"From Transformers to Reformers","authors":"Nauman Riaz, Seemab Latif, R. Latif","doi":"10.1109/ICoDT252288.2021.9441516","DOIUrl":"https://doi.org/10.1109/ICoDT252288.2021.9441516","url":null,"abstract":"This paper investigates different deep learning models for various tasks of Natural Language Processing. Recent ongoing research is about the Transformer models and their variations (like the Reformer model). The Recurrent Neural Networks models were efficient up to an only a fixed size of the window. They were unable to capture long-term dependencies for large sequences. To overcome this limitation, the attention mechanism was introduced which is incorporated in the Transformer model. The dot product attention in transformers has a complexity of O(n2) where n is the sequence length. This computation becomes infeasible for large sequences. Also, the residual layers consume a lot of memory because activations need to be stored for back-propagation. To overcome this limitation of memory efficiency and to make transformers learn over larger sequences, the Reformer models were introduced. Our research includes the evaluation of the performance of these two models on various Natural Language Processing tasks.","PeriodicalId":207832,"journal":{"name":"2021 International Conference on Digital Futures and Transformative Technologies (ICoDT2)","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-05-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114563943","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
Leveraging Supervised Machine Learning Techniques for Identification of Malaria Cells using Blood Smears 利用监督机器学习技术鉴定疟疾细胞使用血液涂片
2021 International Conference on Digital Futures and Transformative Technologies (ICoDT2) Pub Date : 2021-05-20 DOI: 10.1109/ICoDT252288.2021.9441534
Ilsa Rameen, Ayesha Shahadat, Mehwish Mehreen, Saqlain Razzaq, Muhammad Adeel Asghar, Muhammad Jamil Khan
{"title":"Leveraging Supervised Machine Learning Techniques for Identification of Malaria Cells using Blood Smears","authors":"Ilsa Rameen, Ayesha Shahadat, Mehwish Mehreen, Saqlain Razzaq, Muhammad Adeel Asghar, Muhammad Jamil Khan","doi":"10.1109/ICoDT252288.2021.9441534","DOIUrl":"https://doi.org/10.1109/ICoDT252288.2021.9441534","url":null,"abstract":"Plasmodium parasite is identified as amenable for spreading a disease named Malaria. Under the stodgy method, the blood splotch is first smeared on the slide, scrutinized under the microscope, and parasites (which can cause malaria) in blood cells are detected. For beneficial parasite detection, image processing proves to be very much dominant. The reason for this is accuracy in the results. This research presents Malaria detection in blood smear images using supervised learning methods. This proposed method starts with the preprocessing in which images are resized and converted into grayscale. The thresholding technique is implemented to identify blobs for segmentation. For feature extraction, GoogLeNet is maneuvered, and the results of the classification show that this method has an accuracy of 95.8% for detecting malaria in blood smear images.","PeriodicalId":207832,"journal":{"name":"2021 International Conference on Digital Futures and Transformative Technologies (ICoDT2)","volume":"301 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-05-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115442830","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
Large Scale Face Recognition In the Wild: Technical Challenges and Research Directions 野外大规模人脸识别:技术挑战与研究方向
2021 International Conference on Digital Futures and Transformative Technologies (ICoDT2) Pub Date : 2021-05-20 DOI: 10.1109/ICoDT252288.2021.9441525
Abdul Mannan Shahid, M. Fraz, M. Shahzad
{"title":"Large Scale Face Recognition In the Wild: Technical Challenges and Research Directions","authors":"Abdul Mannan Shahid, M. Fraz, M. Shahzad","doi":"10.1109/ICoDT252288.2021.9441525","DOIUrl":"https://doi.org/10.1109/ICoDT252288.2021.9441525","url":null,"abstract":"Face recognition (FR) is the most effective and preferable biometric technique for both verification and identification of humans as compared to iris, voice, retina eye scanning, fingerprint, gait, hand, and ear geometry. FR is the most highlighted and fast-growing research area in computer vision for the past couple of years. It is observed in the literature that most techniques don’t perform well because of unconstrained environments like occlusion, noise, position, angle of view, lighting, illumination, ageing, bad picture quality, low resolution, blurriness, and in many cases uncertainty in data. In this paper, a critical review on prior mentioned issues and their proposed solutions to resolve these issues are analyzed and presented through the state of the art techniques which has been proposed in the literature. Apart from this, it has been observed that various new techniques are applied in the form of loss function revamping, adding regularization, using transfer/reinforcement learning, and some new proposed architectures in the literature.","PeriodicalId":207832,"journal":{"name":"2021 International Conference on Digital Futures and Transformative Technologies (ICoDT2)","volume":"59 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-05-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130872344","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
Motor Speed Synchronization of Mobile Robot Using PI Controller 基于PI控制器的移动机器人电机速度同步
2021 International Conference on Digital Futures and Transformative Technologies (ICoDT2) Pub Date : 2021-05-20 DOI: 10.1109/ICoDT252288.2021.9441518
A. Ashraf, Hira Ahsan, Muhammad Sufyan Arshad
{"title":"Motor Speed Synchronization of Mobile Robot Using PI Controller","authors":"A. Ashraf, Hira Ahsan, Muhammad Sufyan Arshad","doi":"10.1109/ICoDT252288.2021.9441518","DOIUrl":"https://doi.org/10.1109/ICoDT252288.2021.9441518","url":null,"abstract":"Mobile robots due to their ability of movement have proven to find their applications in different fields over the years. Their applications in different fields are due to easy design and manufacturing of the custom platform. Manufacturing of the custom chassis/platforms may result in synchronization issue of motors resulting in detouring of the robot chassis from the path or complexity of the algorithm. To address this issue, design and tuning of a PI controller for a custom built three wheeled mobile robot for synchronization of the motors is discussed in this paper. Results achieved are very close to the desired response of the motors to move the mobile robot in a straight path. Paper highlights the method of designing and tuning a PI controller for wheeled mobile robots.","PeriodicalId":207832,"journal":{"name":"2021 International Conference on Digital Futures and Transformative Technologies (ICoDT2)","volume":"58 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-05-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121959971","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
Smart Wheelchair- An Implementation of Voice and Android Controlled System 智能轮椅-语音和Android控制系统的实现
2021 International Conference on Digital Futures and Transformative Technologies (ICoDT2) Pub Date : 2021-05-20 DOI: 10.1109/ICoDT252288.2021.9441532
M. Amin, Syed Tahir Hussain Rizvi, Sameer Malik, Z. Faheem, Ammar Liaqat
{"title":"Smart Wheelchair- An Implementation of Voice and Android Controlled System","authors":"M. Amin, Syed Tahir Hussain Rizvi, Sameer Malik, Z. Faheem, Ammar Liaqat","doi":"10.1109/ICoDT252288.2021.9441532","DOIUrl":"https://doi.org/10.1109/ICoDT252288.2021.9441532","url":null,"abstract":"The inspiration driving android and voice automated smart wheelchair venture is to construct a smart wheelchair that helps physically impaired people to locomote from one spot then onto the next. To overcome this disability, a smart voice-controlled fully automated wheelchair is designed for physically disabled, patients, or pregnant women. This smart wheelchair will help them move from one place to another without any problem. Numerous wheelchairs are accessible with various running advancements, yet the expense is high and it isn’t much successful. For the most part, designing voice and android control wheelchairs is to conquer a few burdens of the current frameworks. The customer needs to interact with the wheelchair with the help of the application. This framework enables the client to vigorously communicate with the wheelchair at various dimensions of the control (turn left, turn right, proceed, return and stop). This task utilizes a microcontroller circuit and motor drivers to make the development of the wheelchair.","PeriodicalId":207832,"journal":{"name":"2021 International Conference on Digital Futures and Transformative Technologies (ICoDT2)","volume":"207 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-05-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131526646","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
PV Fed Battery and Ultra-Capacitor Based Hybrid Energy Storage for Powering Marine Loads 基于光伏电池和超级电容器的混合储能为船舶负载供电
2021 International Conference on Digital Futures and Transformative Technologies (ICoDT2) Pub Date : 2021-05-20 DOI: 10.1109/ICoDT252288.2021.9441479
M. Tariq, S. Rahman, I. Khan, F. Khan
{"title":"PV Fed Battery and Ultra-Capacitor Based Hybrid Energy Storage for Powering Marine Loads","authors":"M. Tariq, S. Rahman, I. Khan, F. Khan","doi":"10.1109/ICoDT252288.2021.9441479","DOIUrl":"https://doi.org/10.1109/ICoDT252288.2021.9441479","url":null,"abstract":"Corresponding to the worldwide contribution of Renewable Energy Storage systems (RESs), an undeniable surge has been seen in the marine electrical system as well. Meanwhile, To cope with the intermittency of RESs; battery energy storage systems are being embedded in the systems. However, they suffer from low energy density, short life, increased space requirements, and elevated cost. To address these challenges, an ultra-capacitor is recommended to be equipped with battery energy storage. Thus, the integrated system can achieve better dynamic performance by employing comparatively reduced space and higher energy. In order to harness these benefits from this integrated system, optimum management of power generation and consumption must be achieved. This requires the development of an accurate and robust control algorithm. In this paper, an effective control technique is proposed, in which a PV fed Hybrid Energy Storage System (HESS) works in integration with a conventional diesel generator for feeding marine loads mainly lighting and heating. Furthermore, Various possible modes of operation to attain optimum performance such as, considering PV power generation discrepancy, are discussed and validated with simulation results. Whereas, some of the proposed control scheme’s main contributions are, Maximum power extraction from PV panels, unity power factor operation of the utility grid, and increased reliability for the connected loads.","PeriodicalId":207832,"journal":{"name":"2021 International Conference on Digital Futures and Transformative Technologies (ICoDT2)","volume":"88 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-05-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131577108","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
CSOA-Based Residential Energy Management System in Smart Grid Considering DGs for Demand Response 考虑dg需求响应的智能电网中基于csoa的住宅能源管理系统
2021 International Conference on Digital Futures and Transformative Technologies (ICoDT2) Pub Date : 2021-05-20 DOI: 10.1109/ICoDT252288.2021.9441484
M. Waseem, Farzana Kouser, A. Waqas, N. Imran, Sana Hameed, Z. Faheem, Rehan Liaqat, Umair Shabbir
{"title":"CSOA-Based Residential Energy Management System in Smart Grid Considering DGs for Demand Response","authors":"M. Waseem, Farzana Kouser, A. Waqas, N. Imran, Sana Hameed, Z. Faheem, Rehan Liaqat, Umair Shabbir","doi":"10.1109/ICoDT252288.2021.9441484","DOIUrl":"https://doi.org/10.1109/ICoDT252288.2021.9441484","url":null,"abstract":"The increase in energy consumption in the residential sector due to overpopulation has adverse effects on the power system. The traditional power grid is unable to handle a sustainable supply of energy for consumers. The adoption of smart grid and distributed generation sources (DGs) can play a vital role to cope with this challenge of a constant supply of energy retainment. In this paper, DGs like photovoltaic (PV) and battery storage system (BSS) are considered with home to grid (H2G) mutual exchange for residential consumers energy cost reduction based upon real time price signal (RTP). The Crow Search Optimization Algorithm (CSOA) has been applied for energy management controller (EMC) in home energy management (HEM) system to schedule home appliances optimally. It is evident from the analysis that DGs and H2G are important in minimizing consumption cost by an effective HEM system. The results attained from the CSOA proves that the approach is useful for residential consumers. The energy consumption cost is minimized in the proposed scheme taking consumers priorities into consideration. The results are helpful to initiate different demand response programs in the context of both consumers and power system operator.","PeriodicalId":207832,"journal":{"name":"2021 International Conference on Digital Futures and Transformative Technologies (ICoDT2)","volume":"51 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-05-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132176167","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
A Survey of Sentiment Analysis of Internet Textual Data and Application to Pakistani YouTube User Comments 互联网文本数据情感分析研究及在巴基斯坦YouTube用户评论中的应用
2021 International Conference on Digital Futures and Transformative Technologies (ICoDT2) Pub Date : 2021-05-20 DOI: 10.1109/ICoDT252288.2021.9441524
Mehwish Rani, Seemab Latif, Muhaammad Ali Tahir, R. Mumtaz
{"title":"A Survey of Sentiment Analysis of Internet Textual Data and Application to Pakistani YouTube User Comments","authors":"Mehwish Rani, Seemab Latif, Muhaammad Ali Tahir, R. Mumtaz","doi":"10.1109/ICoDT252288.2021.9441524","DOIUrl":"https://doi.org/10.1109/ICoDT252288.2021.9441524","url":null,"abstract":"With the advent of social media, e-commerce and video sharing websites, a large amount of textual data depicting people’s opinions is being generated. This text has a great impact on other web users, product sellers and content creators. Text mining and emotion detection using text analysis has prospered a lot in recent years. Sentiment Analysis is the method of mining emotions, reviews and opinions of web users. In this paper, a survey of text Sentiment Analysis techniques is presented. Sentiment Analysis is applied to comments extracted from Pakistani news videos. Different machine learning algorithms previously surveyed in this paper have been applied to this dataset. Our results have shown that transfer learning can be effectively used for Sentiment Analysis.","PeriodicalId":207832,"journal":{"name":"2021 International Conference on Digital Futures and Transformative Technologies (ICoDT2)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-05-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124840889","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
Tuning of PID Controller Using Whale Optimization Algorithm for Different Systems 基于鲸鱼优化算法的不同系统PID控制器整定
2021 International Conference on Digital Futures and Transformative Technologies (ICoDT2) Pub Date : 2021-05-20 DOI: 10.1109/ICoDT252288.2021.9441526
Uzair Khaleeq uz Zaman, Kanwal Naveed, Atal.A. Kumar
{"title":"Tuning of PID Controller Using Whale Optimization Algorithm for Different Systems","authors":"Uzair Khaleeq uz Zaman, Kanwal Naveed, Atal.A. Kumar","doi":"10.1109/ICoDT252288.2021.9441526","DOIUrl":"https://doi.org/10.1109/ICoDT252288.2021.9441526","url":null,"abstract":"In this paper, a recently developed meta-heuristic optimization method, Whale optimization Algorithm (WOA) is used to tune the parameters of PID controller for different systems. The algorithm is evaluated by setting integral absolute error and integral time absolute error as objective function for various transfer functions. The results obtained are compared with Ziegler-Nichols (Z-N), Genetic Algorithm (GA) and Particle Swarm Optimization (PSO). The results prove the effectiveness of the proposed algorithm and provides the researchers with options for improved system performance.","PeriodicalId":207832,"journal":{"name":"2021 International Conference on Digital Futures and Transformative Technologies (ICoDT2)","volume":"40 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-05-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124375693","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
首页 上一页 下一页 尾页
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整，为了账户安全，请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
请完成安全验证×
相关产品
×
本文献相关产品
联系我们：info@booksci.cn Book学术提供免费学术资源搜索服务，方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号：604180095
Book学术官方微信