Nadeem Zaidkilani, M. Abdel-Nasser, M. García, D. Puig
{"title":"Breast Ultrasound CAD System Based on Efficient Tumour Segmentation Network and Transfer-Learned Features","authors":"Nadeem Zaidkilani, M. Abdel-Nasser, M. García, D. Puig","doi":"10.1109/IMPACT55510.2022.10029203","DOIUrl":"https://doi.org/10.1109/IMPACT55510.2022.10029203","url":null,"abstract":"Breast cancer is the second most common type of cancer worldwide after lung cancer and the leading cause of cancer death among women. Over the past few decades, computer-assisted diagnostic (CAD) systems have been implemented to assist physicians. This paper introduces a CAD system to segment tumours in breast ultrasound (BUS) images and classifies them as benign or malignant. The CAD system has two stages: segmentation and classification. In the segmentation stage, we have developed an encoder-decoder network based on different backbones with various loss functions to segment the tumours. We have fine-tuned the MobileNetv2 network in the classification stage to classify the segmented tumours as benign or malignant. Our experiments demonstrate that WideResNet with BCE and Dice loss function outperforms and yields the best tumour segmentation results with a Dice score of 77.32%. The CAD system achieves a classification accuracy of 86%.","PeriodicalId":300301,"journal":{"name":"2022 5th International Conference on Multimedia, Signal Processing and Communication Technologies (IMPACT)","volume":"42 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125557177","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}
Shanur Rahman, Yusuf Ahmed Khan, Yash Pratap Singh, S. A. Ali, M. Wajid
{"title":"TinyML based Classification of Fetal Heart Rate using Mother’s Abdominal ECG Signal","authors":"Shanur Rahman, Yusuf Ahmed Khan, Yash Pratap Singh, S. A. Ali, M. Wajid","doi":"10.1109/IMPACT55510.2022.10029140","DOIUrl":"https://doi.org/10.1109/IMPACT55510.2022.10029140","url":null,"abstract":"ECG plays a vital role in the field of medical science. The proposed machine learning model is able to classify the heart rate of the fetus through ECG signals that are collected from the mother’s womb. The noise and interference have been reduced in the ECG signal by preprocessing. The proposed Recurrent neural network (RNN) architecture is made on edge impulse. The potential efficiency of the designed model is studied by varying parameters such as kernel size, learning rate, epochs, etc using the abdominal and direct fetal ECG Database from the physionet. During training, the classification of heart rate using ECG signals has achieved 75% accuracy. The beauty of the model is that it is designed with tinyML for implementation on embedded systems.","PeriodicalId":300301,"journal":{"name":"2022 5th International Conference on Multimedia, Signal Processing and Communication Technologies (IMPACT)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126750996","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}
{"title":"A Compact Size and High Isolation Dual-band MIMO Antenna Using EMSIW","authors":"S. A. Ali, M. Wajid, M. Hashmi, Muhammad S. Alam","doi":"10.1109/IMPACT55510.2022.10029292","DOIUrl":"https://doi.org/10.1109/IMPACT55510.2022.10029292","url":null,"abstract":"A simple and low-profile four-elements dual-band multiple-input multiple-output (MIMO) antenna using an eighth mode substrate integrated waveguide (EMSIW) cavity resonator is proposed for 5G new radio. The dual-band operation is achieved by radiating the edge perpendicular to the EMSIW and an extra slot etched out in the proposed structure. Different variations of the size of radiating edges and slots were carried out, and the simulated results were presented. Finally, the optimized antenna is demonstrated to operate at 2.6 GHz (n41) and 3.5 GHz (n78), having 6-dB impedance bandwidths of 6.55 % and 1.91 %, respectively. The four EMSIW elements are counterclockwise arranged to form the MIMO antenna and achieve good diversity performance. Because of the asymmetric EMSIW structure, their radiation patterns are found isolated from each other, thus improving the diversity. As a result, high isolation (>39dB), and envelope correlation coefficient (ECC) is found to be <0.06 without using a complex decoupling network. The prototype of the proposed antenna is developed, and its performances are measured and found in close agreement with the simulated results.","PeriodicalId":300301,"journal":{"name":"2022 5th International Conference on Multimedia, Signal Processing and Communication Technologies (IMPACT)","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124494440","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}
{"title":"Smart Construction Sites in KSA: Challenges and Prospects","authors":"Ahmad Sharqi, Mohamed Ridha El Ouni, S. Alsulamy","doi":"10.1109/IMPACT55510.2022.10029034","DOIUrl":"https://doi.org/10.1109/IMPACT55510.2022.10029034","url":null,"abstract":"Due to the emerging technologies revolution worldwide, the need to exploit and employ innovative technologies for other functions and purposes in different aspects became a remarkable matter. Saudi Arabia is considered as one of the powerful economic countries in the world, where the construction sector participates effectively in its economy. Thus, the construction sector in KSA should convoy the rapid digital revolution and transformation and implement smart devices in sites. A Smart Construction Site (SCS) includes smart devices, Artificial Intelligence, Internet of Things, Augmented Reality, Building Information Modeling, Geographical Information System and cloud information. This paper aims to study the level of implementation of SCS in KSA, analyze obstacles and challenges of adopting SCS and find out the critical success factors for its implementation. A survey of close-ended questions (multi-choices) has been conducted to professionals in the construction sector of Saudi Arabia. consequently, five close-ended questions with multi-choices type have been also prepared, these questions have been derived from a previous study implemented in the United Kingdom (UK) and the Dominican Republic (DR), these questions have been rearranged and organized to fit the structured survey in order to place the Kingdom of Saudi Arabia in comparison with the United Kingdom (UK) as well as the Dominican Republic (DR). total of one hundred respondents have participated in this survey from all regions of Kingdom of Saudi Arabia: southern, central, western, eastern and northern regions. The drivers, obstacles and success factors for implementing smart devices and technologies in KSA’s construction sector have been investigated and analyzed. Besides, It has been concluded that KSA is on the right path toward adopting smart construction sites with attractive results compared and even better than the UK in some factors.","PeriodicalId":300301,"journal":{"name":"2022 5th International Conference on Multimedia, Signal Processing and Communication Technologies (IMPACT)","volume":"88 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115858984","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}
Amarjeet Singh, V. Singh, A. Aggarwal, S. Aggarwal
{"title":"Improving Business deliveries using Continuous Integration and Continuous Delivery using Jenkins and an Advanced Version control system for Microservices-based system","authors":"Amarjeet Singh, V. Singh, A. Aggarwal, S. Aggarwal","doi":"10.1109/IMPACT55510.2022.10029149","DOIUrl":"https://doi.org/10.1109/IMPACT55510.2022.10029149","url":null,"abstract":"For enterprise application various software development models are available. Out of these available software development models, micro-services architecture has gained a lot of popularity. The micro-service architecture fits well to an enterprise applications which are usually complex in nature and requires out of box scalability along with low latency. Micro-services in containerized cloud environment are very useful for enterprise applications. From the software development perspective in a software industry it is also very crucial to identify and rectify the defects at an early development phase rather than at production environment level. Few earlier published works had a focus on micro-services while few others on the issues and challenges of Kubernetes. However, to the best of our knowledge, the relationship between these two has not been worked out earlier. This is the key focus area of this work. This work focuses on identifying the defects at an early stage for micro-services that are deployed on Kubernetes. Few basic guidelines are proposed for a micro-service architecture based on automation, fault design, design philosophy, naming convention, monitoring and warning.","PeriodicalId":300301,"journal":{"name":"2022 5th International Conference on Multimedia, Signal Processing and Communication Technologies (IMPACT)","volume":"123 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131978604","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}
{"title":"Logic Circuit Implementation for Enabling SRAM Based In Memory Computing","authors":"Md Izhar, Sayeed Ahmad, S. Rahman","doi":"10.1109/IMPACT55510.2022.10029072","DOIUrl":"https://doi.org/10.1109/IMPACT55510.2022.10029072","url":null,"abstract":"Von-Neumann architecture which physically decouples the storage/memory and processing blocks suffers from well-known memory bottleneck. In-memory computing (IMC) is a promising architecture to cope up with this bottleneck, where memory performs the computation along with its usual storage function. This paper presents the implementation of the half adder and half-subtractor circuits using the 6T SRAM architecture. The circuits require minimal peripheral changes. It also proposes the implementation of 2×1 multiplexer using the concept of copy operation within SRAM cells without using much peripheral circuitries. The simulation results confirm the logic functionality for all the possible cases. Since our proposals maintain the 6T-SRAM architecture with minimal peripherals, it can be used as a memory unit with usual read-write operation and also as an on-demand basic computing unit.","PeriodicalId":300301,"journal":{"name":"2022 5th International Conference on Multimedia, Signal Processing and Communication Technologies (IMPACT)","volume":"1087 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132006262","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}
{"title":"Deep Learning Framework using CNN for Brain Tumor Classification","authors":"Neha Bhardwaj, M. Sood, SS Gill","doi":"10.1109/IMPACT55510.2022.10029043","DOIUrl":"https://doi.org/10.1109/IMPACT55510.2022.10029043","url":null,"abstract":"The brain tumor is one of the major concerns accounting to number of deaths caused by it worldwide. The available techniques to diagnose brain tumors requires human intervention, are time consuming and are subjective in nature. In the current scenario, automated methods for correct diagnosis of brain tumors is of utmost importance for timely detection and proper diagnosis. The existing frameworks are time consuming and intrusive, these limitations highlight the importance of using a fully automated deep learning system for brain tumour classification. The paper presents a deep learning framework for classification with minimal human intervention. Convolutional Neural Network is most preferred deep learning method for classification tasks owing to its flexible architecture and high accuracy. This paper aims to develop a deep learning based CNN framework for brain tumor classification. The proposed CNN framework has an edge over the other models by achieving classification accuracy of 99.4% and loss of 0.0030%. The Comparative analysis of the proposed framework with other state of art models shows a relative improvement in accuracy and test error.","PeriodicalId":300301,"journal":{"name":"2022 5th International Conference on Multimedia, Signal Processing and Communication Technologies (IMPACT)","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133983954","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}
{"title":"On Green Supplier Selection Problem Utilizing Modified TOPSIS with R-norm Picture Fuzzy Discriminant Measure","authors":"A. Singh, Himanshu Dhumras, R. Bajaj","doi":"10.1109/IMPACT55510.2022.10029080","DOIUrl":"https://doi.org/10.1109/IMPACT55510.2022.10029080","url":null,"abstract":"Picture fuzzy sets (PFSs) hold great importance when one needs to arrive to a decision in a MCDM (Multi criteria decision making) scenario, especially when the available information is inconsistent, incomplete and inexact. Through this communication, we introduce a novel concept of a new information measure called R-norm picture fuzzy discriminant measure. The proposed parametric measure then applied in the conventional TOPSIS method for solving a decision-making problem. In particular, we have applied the proposed measure and the modified TOPSIS technique to solve a green supplier selection problem. We have illustrated the effectiveness of our measure for inferring practical relationships between the various alternatives in an uncertain setting.","PeriodicalId":300301,"journal":{"name":"2022 5th International Conference on Multimedia, Signal Processing and Communication Technologies (IMPACT)","volume":"73 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131584163","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}
{"title":"A hybrid framework to prevent VANET from Sybil Attack","authors":"Syed Mohd Faisal, Bineet Kumar Gupta, T. Zaidi","doi":"10.1109/IMPACT55510.2022.10029103","DOIUrl":"https://doi.org/10.1109/IMPACT55510.2022.10029103","url":null,"abstract":"The commuter having mobile vehicle attain a widespread safety with the proper use of Vehicular Ad-hoc Network (VANET). Instead of apparent most of the opaque services are raising its hands to adapt safety advancement through VANET. VANETs let road authorities monitor and track vehicles to prevent unsafe driving and provide quick assistance. However, these networks pose architecture, routing, communication, and security challenges as well as these networks are vulnerable to security breaches due to wireless channels. Multiple-identity malicious vehicles threaten the long-term sustainability of networks. VANET is vulnerable to attacks due to lack of infrastructure. One of the most catastrophic attack is Sybil's attack. Sybil vehicles on VANET can spread false information about traffic, an accident, or a roadblock. The driver could be forced to take a route as a result, putting him in risk of an unfortunate event. This paper discusses VANET technology's Sybil-caused limitations. The paper also proposes a hybrid method which is the combination of position-based verification and trust certification method to detect and prevent Sybil attacks.","PeriodicalId":300301,"journal":{"name":"2022 5th International Conference on Multimedia, Signal Processing and Communication Technologies (IMPACT)","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115445186","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}
{"title":"A Non-linear Synapse Neural Network with O(N) Neurons for Graph Colouring","authors":"Syed Atiqur Rahman, Mohd Kashif","doi":"10.1109/IMPACT55510.2022.10029148","DOIUrl":"https://doi.org/10.1109/IMPACT55510.2022.10029148","url":null,"abstract":"A feedback artificial neural network with nonlinear synaptic connections is proposed for the classical graph colouring problem. The network employs O(N) Neurons with O(N2) non-linear synapses for a graph with N nodes. The network has a transcendental energy function that is fundamentally different from Hopfield Network. The proposed network always converges to a feasible solution, with the number of assigned colours being nearly equal to the Chromatic number of the corresponding graph. HSPICE simulation confirms the functioning of the proposed circuit. The results are compared with the existing circuits to highlight the significant reduction in the number of colours required for colouring a given graph.","PeriodicalId":300301,"journal":{"name":"2022 5th International Conference on Multimedia, Signal Processing and Communication Technologies (IMPACT)","volume":"44 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124444265","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}