Pub Date : 2023-03-17DOI: 10.1109/iCoMET57998.2023.10099210
Sanaullah Khan, S. Afridi, Lubina Iram, Tehseenullah Khan
This work presents the new design approach to enhance the spurious performance of monolithic ceramic waveguide filters with better selectivity. The monolithic ceramic waveguide filters offer considerable miniaturization when compared to TEM filters. Resonators of different widths with metal plated blind holes were used to achieve inter-resonator coupling and transmission zero while improving the stop band rejection of the filter. The proposed filter achieved excellent stop band performance of 1.65*f_o as compared to same width monolithic ceramic waveguide filter. The simulated results of 3rd order and 4th order filter were presented in this paper.
{"title":"Ceramic Waveguide Filters with Improved Stop band Rejection and Transmission Zeros","authors":"Sanaullah Khan, S. Afridi, Lubina Iram, Tehseenullah Khan","doi":"10.1109/iCoMET57998.2023.10099210","DOIUrl":"https://doi.org/10.1109/iCoMET57998.2023.10099210","url":null,"abstract":"This work presents the new design approach to enhance the spurious performance of monolithic ceramic waveguide filters with better selectivity. The monolithic ceramic waveguide filters offer considerable miniaturization when compared to TEM filters. Resonators of different widths with metal plated blind holes were used to achieve inter-resonator coupling and transmission zero while improving the stop band rejection of the filter. The proposed filter achieved excellent stop band performance of 1.65*f_o as compared to same width monolithic ceramic waveguide filter. The simulated results of 3rd order and 4th order filter were presented in this paper.","PeriodicalId":369792,"journal":{"name":"2023 4th International Conference on Computing, Mathematics and Engineering Technologies (iCoMET)","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126426294","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 : 2023-03-17DOI: 10.1109/iCoMET57998.2023.10099279
Muhammad Rizwan Siddique, Syed Irtiza Ali Shah, Ammad Ahmed, M. Mehmood
The braking system of a train is not exactly similar to that of other vehicles. This is because of the uneven distribution of mass and.,hence., the different requirement of braking force along the train. In this project we investigate the different braking systems of trains and their integration with advanced controls. We then propose a closed loop system that takes into account the behavior of the driver and the dynamics of the train in order to provide an effective braking mechanism. A controller is designed for an assumed model of a train which shows only 5% error in the achieved speed after braking. The controller stabilizes the braking force in accordance with the driver's input which leads to a more efficient braking process. We propose a control system that takes multiple inputs from the train components and uses them to analyze and process a calculated braking output which stops the train within the required distance while keeping a stable deceleration. Such an approach eases the driving conditions for the driver and also maximizes the efficiency of the braking process of train.
{"title":"Vehicle response control during stopping a train with dynamics of the train and driver","authors":"Muhammad Rizwan Siddique, Syed Irtiza Ali Shah, Ammad Ahmed, M. Mehmood","doi":"10.1109/iCoMET57998.2023.10099279","DOIUrl":"https://doi.org/10.1109/iCoMET57998.2023.10099279","url":null,"abstract":"The braking system of a train is not exactly similar to that of other vehicles. This is because of the uneven distribution of mass and.,hence., the different requirement of braking force along the train. In this project we investigate the different braking systems of trains and their integration with advanced controls. We then propose a closed loop system that takes into account the behavior of the driver and the dynamics of the train in order to provide an effective braking mechanism. A controller is designed for an assumed model of a train which shows only 5% error in the achieved speed after braking. The controller stabilizes the braking force in accordance with the driver's input which leads to a more efficient braking process. We propose a control system that takes multiple inputs from the train components and uses them to analyze and process a calculated braking output which stops the train within the required distance while keeping a stable deceleration. Such an approach eases the driving conditions for the driver and also maximizes the efficiency of the braking process of train.","PeriodicalId":369792,"journal":{"name":"2023 4th International Conference on Computing, Mathematics and Engineering Technologies (iCoMET)","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125392008","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 : 2023-03-17DOI: 10.1109/iCoMET57998.2023.10099183
Arjeton Uzairi, Arianit Kurti, Zenun Kastrati
Labeling of trademark images with Vienna codes from the Vienna classification is a manual process carried out by domain experts by searching trademark image databases using specific keywords. Manual labeling is both a time-consuming and error-prone process. Therefore, in this paper, we investigate how deep learning techniques can improve and automate labeling of new unlabeled trademark images. Three different deep learning models, namely CNN, LSTM and GRU, are trained and tested on a collected dataset composed of 14,500 unique logos extracted from the European Union Intellectual Property Office Open Data Portal. A set of controlled experiments establishing baseline results on the dataset showed that CNN outperforms the other two models in terms of both accuracy and training time. The experimental results also suggest that deep learning models are an important tool that can be applied by Intellectual Property Offices in real-world applications to automate the trademark image classification task.
{"title":"A Deep Learning-based Solution for Identification of Figurative Elements in Trademark Images","authors":"Arjeton Uzairi, Arianit Kurti, Zenun Kastrati","doi":"10.1109/iCoMET57998.2023.10099183","DOIUrl":"https://doi.org/10.1109/iCoMET57998.2023.10099183","url":null,"abstract":"Labeling of trademark images with Vienna codes from the Vienna classification is a manual process carried out by domain experts by searching trademark image databases using specific keywords. Manual labeling is both a time-consuming and error-prone process. Therefore, in this paper, we investigate how deep learning techniques can improve and automate labeling of new unlabeled trademark images. Three different deep learning models, namely CNN, LSTM and GRU, are trained and tested on a collected dataset composed of 14,500 unique logos extracted from the European Union Intellectual Property Office Open Data Portal. A set of controlled experiments establishing baseline results on the dataset showed that CNN outperforms the other two models in terms of both accuracy and training time. The experimental results also suggest that deep learning models are an important tool that can be applied by Intellectual Property Offices in real-world applications to automate the trademark image classification task.","PeriodicalId":369792,"journal":{"name":"2023 4th International Conference on Computing, Mathematics and Engineering Technologies (iCoMET)","volume":"89 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125670524","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 : 2023-03-17DOI: 10.1109/iCoMET57998.2023.10099152
Muhammad Sarim Amir, Gufran Bhatti, Misbah Anwer, Yumna Iftikhar
Everything is evolving toward IoT (Internet of Things) and online-based in our technological environment. The number of IoT devices and ubiquitous computing systems are growing exponentially. This also increases the risk of network breach. To cater this issue many researchers proposed different techniques and get great results but it can be better since everything in online and it's a matter of security and privacy. This paper presents an efficient and sustainable intrusion detection system by the concatenation of two well-known state of the art “kitsune” datasets (ARP MITM and SSDP Flood). Random Forest, decision tree, and Bi-LSTM (Bi-Directional Long Short Term Memory) were implemented in different training and testing ratios and different numbers of layers. Performance measures show that all the models achieved over 99% accuracy but random forest outperforms both models on the concatenated dataset. Both attacks are determined by the given model hence increasing the performance and the system will notify in case of any malicious activity.
{"title":"Efficient & Sustainable Intrusion Detection System Using Machine Learning & Deep Learning for IoT","authors":"Muhammad Sarim Amir, Gufran Bhatti, Misbah Anwer, Yumna Iftikhar","doi":"10.1109/iCoMET57998.2023.10099152","DOIUrl":"https://doi.org/10.1109/iCoMET57998.2023.10099152","url":null,"abstract":"Everything is evolving toward IoT (Internet of Things) and online-based in our technological environment. The number of IoT devices and ubiquitous computing systems are growing exponentially. This also increases the risk of network breach. To cater this issue many researchers proposed different techniques and get great results but it can be better since everything in online and it's a matter of security and privacy. This paper presents an efficient and sustainable intrusion detection system by the concatenation of two well-known state of the art “kitsune” datasets (ARP MITM and SSDP Flood). Random Forest, decision tree, and Bi-LSTM (Bi-Directional Long Short Term Memory) were implemented in different training and testing ratios and different numbers of layers. Performance measures show that all the models achieved over 99% accuracy but random forest outperforms both models on the concatenated dataset. Both attacks are determined by the given model hence increasing the performance and the system will notify in case of any malicious activity.","PeriodicalId":369792,"journal":{"name":"2023 4th International Conference on Computing, Mathematics and Engineering Technologies (iCoMET)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127993839","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 : 2023-03-17DOI: 10.1109/iCoMET57998.2023.10099312
M. Rafiq, Muhammad Sarwar Ehsan, Asfar Nisar, Samra Abbas
In this manuscript, a mathematical model of a rotavirus infection integrating the vaccinated class is numerically analyzed. Efficient numerical analysis of an epidemic model includes three main features positivity, boundedness, and dynamical consistency. These characteristics have been observed by using various numerical techniques. Standard finite difference scheme, Euler's, RK-4 is widely used to solve non-linear mathematical models. Unfortunately, these schemes have some limitations and do not preserve the essential features of the mathematical model. A competitive non-standard finite difference (NSFD) scheme is proposed to discuss the dynamics of rotavirus in a population. The proposed scheme exhibits the true behavior of the rotavirus disease and shows a good agreement with the theoretical findings. Moreover, the impact of vaccines on the rotavirus dynamics has also been studied.
{"title":"Computationally Efficient Numerical Analysis of Rotavirus Epidemic Model","authors":"M. Rafiq, Muhammad Sarwar Ehsan, Asfar Nisar, Samra Abbas","doi":"10.1109/iCoMET57998.2023.10099312","DOIUrl":"https://doi.org/10.1109/iCoMET57998.2023.10099312","url":null,"abstract":"In this manuscript, a mathematical model of a rotavirus infection integrating the vaccinated class is numerically analyzed. Efficient numerical analysis of an epidemic model includes three main features positivity, boundedness, and dynamical consistency. These characteristics have been observed by using various numerical techniques. Standard finite difference scheme, Euler's, RK-4 is widely used to solve non-linear mathematical models. Unfortunately, these schemes have some limitations and do not preserve the essential features of the mathematical model. A competitive non-standard finite difference (NSFD) scheme is proposed to discuss the dynamics of rotavirus in a population. The proposed scheme exhibits the true behavior of the rotavirus disease and shows a good agreement with the theoretical findings. Moreover, the impact of vaccines on the rotavirus dynamics has also been studied.","PeriodicalId":369792,"journal":{"name":"2023 4th International Conference on Computing, Mathematics and Engineering Technologies (iCoMET)","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131654511","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 : 2023-03-17DOI: 10.1109/icomet57998.2023.10099129
{"title":"Sustainable Technologies for Socio-Economic Development","authors":"","doi":"10.1109/icomet57998.2023.10099129","DOIUrl":"https://doi.org/10.1109/icomet57998.2023.10099129","url":null,"abstract":"","PeriodicalId":369792,"journal":{"name":"2023 4th International Conference on Computing, Mathematics and Engineering Technologies (iCoMET)","volume":"66 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126200085","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 : 2023-03-17DOI: 10.1109/iCoMET57998.2023.10099242
Muhammad Hasham Qazi, Muhammad Palize Qazi
This paper introduces VAIFU, a Virtual Agent for Introducing and Familiarizing Users in Virtual Reality. VAIFU is an interactive embodied conversational agent that allows for both speech interaction and physical interactions in Virtual Reality. The goal of VAIFU is to introduce and familiarize new users with the landscape of virtual reality. The paper discusses the system design, agent development, interaction methods, and natural language processing techniques that may be used in order to develop such an agent for immersive human-like social interactions and how these social features may be beneficial to users. The paper concludes with a pilot study and future work for further iterations of the project.
{"title":"Introducing VAIFU: A Virtual Agent for Introducing and Familiarizing Users in VR","authors":"Muhammad Hasham Qazi, Muhammad Palize Qazi","doi":"10.1109/iCoMET57998.2023.10099242","DOIUrl":"https://doi.org/10.1109/iCoMET57998.2023.10099242","url":null,"abstract":"This paper introduces VAIFU, a Virtual Agent for Introducing and Familiarizing Users in Virtual Reality. VAIFU is an interactive embodied conversational agent that allows for both speech interaction and physical interactions in Virtual Reality. The goal of VAIFU is to introduce and familiarize new users with the landscape of virtual reality. The paper discusses the system design, agent development, interaction methods, and natural language processing techniques that may be used in order to develop such an agent for immersive human-like social interactions and how these social features may be beneficial to users. The paper concludes with a pilot study and future work for further iterations of the project.","PeriodicalId":369792,"journal":{"name":"2023 4th International Conference on Computing, Mathematics and Engineering Technologies (iCoMET)","volume":"185 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116425653","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}
Distributed agile development comes with a lot of challenges in particular as it has to do with agile teams working together from different geological locations on the same project. Most probably it happens due to a lack of visibility in the complex development and deployment process, poor communication, and unavailability of the development team and corresponding customer in the same place. These factors affect the performance of the team and increase the overall cost of development. To mitigate all these aspects, we proposed a cloud computing-based Infrastructure which is a combination of both agile as well as cloud computing technology named ‘CBAI’. The proposed Infrastructure assists the team members to work efficiently even if they are different geo-locations without burdening the cost. It provides the basic structure for global agile development and is also efficient in reducing the technical liability, and the need for project backlog.
{"title":"CBAI: Cloud-Based Agile Infrastructure for Enhancing Distributed Agile Development","authors":"Muhammad Ali, Sehrish Munawar Cheema, Zaheer Aslam, Ammerha Naz, Nasir Ayub","doi":"10.1109/iCoMET57998.2023.10099284","DOIUrl":"https://doi.org/10.1109/iCoMET57998.2023.10099284","url":null,"abstract":"Distributed agile development comes with a lot of challenges in particular as it has to do with agile teams working together from different geological locations on the same project. Most probably it happens due to a lack of visibility in the complex development and deployment process, poor communication, and unavailability of the development team and corresponding customer in the same place. These factors affect the performance of the team and increase the overall cost of development. To mitigate all these aspects, we proposed a cloud computing-based Infrastructure which is a combination of both agile as well as cloud computing technology named ‘CBAI’. The proposed Infrastructure assists the team members to work efficiently even if they are different geo-locations without burdening the cost. It provides the basic structure for global agile development and is also efficient in reducing the technical liability, and the need for project backlog.","PeriodicalId":369792,"journal":{"name":"2023 4th International Conference on Computing, Mathematics and Engineering Technologies (iCoMET)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129896708","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 : 2023-03-17DOI: 10.1109/iCoMET57998.2023.10099300
Faisal Nawab, A. Ibrahim, Shaikh Zeeshan Suheel, Adamu Ahmed Goje
The most important factor to take into account when building solar energy systems is solar irradiation. It is impossible to measure sun irradiation everywhere due to its high cost and difficulties. Additionally, in some places, the GHI was overpredicted by 25% by NASA satellite data. The main goal of this study was to develop an artificial neural network (ANN) model that can reduce the error in satellite data by predicting global horizontal irradiation (GHI) using inputs from satellite data obtained from the NASA Power Data viewer. The MAPE in the satellite was decreased by 35.8% in Peshawar, 10.2% in Islamabad, and 8.9% in Multan using the ANN models. Additionally, the results showed that all ANN models' predictions were more precise than satellite data.
{"title":"Comparison of ANN Global Horizontal Irradiation predictions with Satellite Global Horizontal Irradiation using Statistical evaluation","authors":"Faisal Nawab, A. Ibrahim, Shaikh Zeeshan Suheel, Adamu Ahmed Goje","doi":"10.1109/iCoMET57998.2023.10099300","DOIUrl":"https://doi.org/10.1109/iCoMET57998.2023.10099300","url":null,"abstract":"The most important factor to take into account when building solar energy systems is solar irradiation. It is impossible to measure sun irradiation everywhere due to its high cost and difficulties. Additionally, in some places, the GHI was overpredicted by 25% by NASA satellite data. The main goal of this study was to develop an artificial neural network (ANN) model that can reduce the error in satellite data by predicting global horizontal irradiation (GHI) using inputs from satellite data obtained from the NASA Power Data viewer. The MAPE in the satellite was decreased by 35.8% in Peshawar, 10.2% in Islamabad, and 8.9% in Multan using the ANN models. Additionally, the results showed that all ANN models' predictions were more precise than satellite data.","PeriodicalId":369792,"journal":{"name":"2023 4th International Conference on Computing, Mathematics and Engineering Technologies (iCoMET)","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128216388","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 : 2023-03-17DOI: 10.1109/iCoMET57998.2023.10099377
A. R. Shah, Isma Javed, Usman Shams, Muhammad Asif Naverd, M. Q. Mehmood
Human blood scrutinization is an indispensable step to analyze a particular health condition, comprise of a complete blood cell (CBC) count. CBC accentuates the counting of White blood cells (WBCs), red blood cells (RBCs), and Platelets which are implicitly significant for the analysis of severe maladies such as leukemia, thrombocytopenia, and anemia. Traditional approaches like manual counting and automated analyzer were extensively used, which is monotonous, time intensive, and entail a lot of medical experts. To get rid of aforesaid leisure techniques, here by using a machine learning-based object detection and classification algorithm you only look once (YOLO) to count the blood cells. YOLO with modified configuration has been trained on the customized dataset to detect the WBCs, RBCs, and platelets.
{"title":"Disease estimation using robust AI methods","authors":"A. R. Shah, Isma Javed, Usman Shams, Muhammad Asif Naverd, M. Q. Mehmood","doi":"10.1109/iCoMET57998.2023.10099377","DOIUrl":"https://doi.org/10.1109/iCoMET57998.2023.10099377","url":null,"abstract":"Human blood scrutinization is an indispensable step to analyze a particular health condition, comprise of a complete blood cell (CBC) count. CBC accentuates the counting of White blood cells (WBCs), red blood cells (RBCs), and Platelets which are implicitly significant for the analysis of severe maladies such as leukemia, thrombocytopenia, and anemia. Traditional approaches like manual counting and automated analyzer were extensively used, which is monotonous, time intensive, and entail a lot of medical experts. To get rid of aforesaid leisure techniques, here by using a machine learning-based object detection and classification algorithm you only look once (YOLO) to count the blood cells. YOLO with modified configuration has been trained on the customized dataset to detect the WBCs, RBCs, and platelets.","PeriodicalId":369792,"journal":{"name":"2023 4th International Conference on Computing, Mathematics and Engineering Technologies (iCoMET)","volume":"492 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125442146","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：