{"title":"American sign language hand gesture interpreter","authors":"P. Parajuli, A. K. Sharma","doi":"10.1049/icp.2022.0614","DOIUrl":"https://doi.org/10.1049/icp.2022.0614","url":null,"abstract":"For many disabled people who are dumb or deaf sign language is a way of communication, to do communication both people need to know sign language or need a translator between them, but everywhere they are not getting a translator. This project is a prototype that will work as a translator for them so that they can communicate with anyone irrespective of knowledge of sign language. With the help of gestures, we can perform many actions like human-computer interaction, gesture-controlled home appliances, and many applications that use gestures as the trigger input. In this prototype, an image is obtained using a webcam. OpenCV helps in detecting gestures from images. And on a later stage gesture is converted to text. OpenCV is a python package tool that provides support with image processing techniques.","PeriodicalId":224655,"journal":{"name":"7th International Conference on Computing in Engineering & Technology (ICCET 2022)","volume":"127 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127020125","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":"Clustering solutions and analysis for cognitive radio Wireless Sensor Networks","authors":"S. Panbude, B. Iyer, A. Nandgaonkar","doi":"10.1049/icp.2022.0630","DOIUrl":"https://doi.org/10.1049/icp.2022.0630","url":null,"abstract":"Cognitive radio Wireless Sensor Network is one of the emerging technologies to address the challenges of conventional wireless networks. The core functionality of any network like Mobile Ad hoc Network (MANET), Wireless Sensor Network (WSN), etc., is based on the routing mechanism. For CR-WSNs, three types of routing schemes are used such as multihop routing, one-hop routing, and cluster-based routing. Because of the potential for impractical methods with the one-hop routing and the latency correlated with the multihop routing, the cluster-based routing is considered encouraging. Thus clusteringbased solutions received more attention for WSNs and CR-WSNs than other routing strategies. While working with CR-WSNs, the primary constraints are limited processing power and sensor nodes, and hence it is necessary to consider energy-efficient clustering design to enhance the network lifetime. Several clustering solutions are proposed for WSNs. However, it is noticed that clustering methods of WSNs cannot directly be applied to CR-WSNs due to topology variations. Designing the clustering protocol for CR-WSNs is a challenging problem compared to WSN. This article briefly reviews the current clustering protocols in CRSN and performs a comparative performance analysis on some of these protocols. The experimental results are derived through simulation, and the results are plotted for performance parameters such as throughput, packet delivery rate (PDR), overhead, energy consumption, and delay. The paper concludes by focusing on the standard protocols' performance variations.","PeriodicalId":224655,"journal":{"name":"7th International Conference on Computing in Engineering & Technology (ICCET 2022)","volume":"51 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131325768","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}
J. Sanjay Raju, A. Ganesh, M. Muralidharan, V. Raghavan
{"title":"Design and analysis of a system to block reverse flow of blood in intravenous line","authors":"J. Sanjay Raju, A. Ganesh, M. Muralidharan, V. Raghavan","doi":"10.1049/icp.2022.0618","DOIUrl":"https://doi.org/10.1049/icp.2022.0618","url":null,"abstract":"In all hospitals and clinics, intravenous (IV) treatment is a standard way of primary treatment. The IV treatment has one disadvantage: the reverse flow of blood flows back into the intravenous tube. Reverse flow is caused by a pressure difference between the intravenous line and the bodily blood flow. To cope with this issue, hospitals regularly monitor the fluid level present in the intravenous line. Even though they check the level constantly, some cases may miss out. So the only way to solve this problem is though blocking the reverse flow. Although several computerized systems have advanced to make the tracking of intravenous infusion easy for both hospitals and clinics, there is no system to block the reverse flow. In this paper, we propose a servomotor-controlled locking gadget to prevent the backflow of blood by using a non-contact liquid level sensor and a microprocessor. It is easy and affordable, making it available even in less market area places.","PeriodicalId":224655,"journal":{"name":"7th International Conference on Computing in Engineering & Technology (ICCET 2022)","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132235629","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":"Walker-delta constellation design for LEO-based navigation using small satellites","authors":"S. Vemuri, B. Dappuri","doi":"10.1049/icp.2022.0627","DOIUrl":"https://doi.org/10.1049/icp.2022.0627","url":null,"abstract":"The existing Global Navigation Satellite Systems (GNSS) in Medium Earth Orbit (MEO) such as GPS (USA), GLONASS (Russia), Galileo (Europe), and COMPASS/Beidou-2 (China) are deployed at an altitude of 20,000 km. The broad applicability of these systems for indoor positioning and Navigation is limited because these navigation signals typical are in L-band and are 20dB below noise level when received at the receiver on the earth, where received signal power is in order - 120 dBm. There is significant growth in utilizing satellite technology through the low earth orbit (LEO) (typically 400 to 1500 km) for various applications, including communication and internet services, which also paved the way to explore the possibility of deploying satellites to meet navigation and positioning services. This is advantageous over MEO-based GNSS, particularly in terms of stronger signals for the system's users on the earth to achieve resilient positioning (both outdoor and indoor). There are many LEO constellation providers to support communication services, including OneWeb, SpaceX, Boeing, and Iridium. However, a total capacity standalone LEO-based navigation constellation is yet to be deployed. In this paper, a small satellite-based LEO constellation for positioning and Navigation is proposed based on the walker-delta pattern.","PeriodicalId":224655,"journal":{"name":"7th International Conference on Computing in Engineering & Technology (ICCET 2022)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134145739","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}
R. Bhavani, V. Ramkumar, V. Ravindran, R. Sindhuja, K. Swaminathan
{"title":"An efficient SAR image detection based on deep dense-mobile net method","authors":"R. Bhavani, V. Ramkumar, V. Ravindran, R. Sindhuja, K. Swaminathan","doi":"10.1049/icp.2022.0598","DOIUrl":"https://doi.org/10.1049/icp.2022.0598","url":null,"abstract":"Nowadays, many studies are based on the Synthetic aperture radar (SAR) for detecting a ship which is more important for its safety. This method is used to safeguard the ship from lousy weather and reach it on its time. In recent times, the studies are advanced with deep learning for very sensitive calculation with higher accuracy skills; the SAR image is also worked on it. In this brief, the proposed deep learning of hybrid DenseNet and mobile (DMN) is implemented to detect the ship. This technique is based on the convolutional neural network (CNN), a multi-layer classifier. This method combines DenseNet and mobile techniques that are used to classify the missing ship and detect the false alarm with higher precision. The results are simulated and compared with the previous method by validating parameters like precision, recall, and F1 score. The results showed that the proposed DMN is much more effective than the previous deep learning in ship detection.","PeriodicalId":224655,"journal":{"name":"7th International Conference on Computing in Engineering & Technology (ICCET 2022)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122524869","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":"Conquering the COVID-19 pandemic: a deep learning based approach","authors":"S. Parekh, Ronak Agarwal, T. Jadhav, A. Joshi","doi":"10.1049/icp.2022.0586","DOIUrl":"https://doi.org/10.1049/icp.2022.0586","url":null,"abstract":"As the world continues to grapple with COVID-19, public places are opening gradually. However, it is necessary to adhere to the guidelines released by governments across the world to prevent an increase in the number of cases. The major guidelines which have proven to be quite effective include covering one's face and nose and maintaining distance from others. To enforce these guidelines, this work proposes a model to detect and classify people into three classes; wearing mask, no mask, and incorrectly worn mask using the YOLOv5 algorithm for object detection. A novel mathematical formula for distance estimation labels people as safe or unsafe based on the distance maintained from others. This model is trained specifically for helping in the enforcement of the guidelines in the context of reopening of indoor establishments like malls, theatres, and restaurants in India, where the general population makes use of various types of face coverings like handkerchiefs, scarves, face shields in addition to surgical and handmade masks. This work also provides a comparison between Scaled-YOLOv4 and YOLOv5 in terms of their accuracy with a custom dataset. The proposed model achieved a peak accuracy of 94.67% using the YOLOv5 algorithm and an accuracy of 92% for social distance estimation. The model trained using the Scaled-YOLOv4 algorithm achieved a much lower peak accuracy of 74.51%.","PeriodicalId":224655,"journal":{"name":"7th International Conference on Computing in Engineering & Technology (ICCET 2022)","volume":"118 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129109572","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":"Multiclass classification for DDoS attacks using LSTM time-series model","authors":"V. Gaur, A. Dogra, A. Gupta, Abhishek O. Tibrewal","doi":"10.1049/icp.2022.0605","DOIUrl":"https://doi.org/10.1049/icp.2022.0605","url":null,"abstract":"As the penetration of the Internet into the interior of the third world keeps on increasing, more people come onto the Internet to communicate and globalize this behemoth. Thus, generating and consuming large amounts of data. To service the increasing number of customers and their data needs, we need to set up new servers increasingly. Having many people using the Internet can also be a problem as they might be a part of a DDoS attack unknowingly. In Botnet, a Bot-Herder infects many computers with Botnet malware, remotely controlling multiple devices, and makes them accomplices in DDoS attacks. People are getting included in a botnet sphere unknowingly. The traditional cyber security paradigm has become obsolete because of the conventional approaches. Thus, machine learning has become a necessity in DDoS intrusion detection. In DDoS attacks, multiple malicious packets are sent to the server to stagger its bandwidth, buffer, and CPU power. This paper proposes a Time-Series-based Recurrent Neural Network (RNN) model using the LSTM network employed on the CICDDoS2019 dataset. The model outperforms the previous benchmarked models as it achieves maximum value with a 1-layer LSTM model in multiclass grouped classification. The 1- layer LSTM values have F1-Score, Recall, and Precision are 0.980, 0.975, and 0.988, respectively.","PeriodicalId":224655,"journal":{"name":"7th International Conference on Computing in Engineering & Technology (ICCET 2022)","volume":"104 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123519775","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":"Children biometric recognition for the betterment of society using deep intelligence","authors":"V. Kamble, M. Dale","doi":"10.1049/icp.2022.0613","DOIUrl":"https://doi.org/10.1049/icp.2022.0613","url":null,"abstract":"Missing and abduction of children is a big social issue nowadays. According to the National Crime Records Bureau, India reports more than 100 children go missing every day. Children are in the developing stage till their adulthood. Their biometrics also go through many changes. Therefore, biometric identification system for children is not yet developed. Children's recognition using their biometrics is a challenging task. Many researchers are working on this problem using different biometrics, such as finger, foot, palmprint, face, iris, ear and headprint. However, the issue is not yet resolved satisfactorily. The problem in recognizing children is the small size of biometrics. It is under developing stage, therefore displacement of key features observed, which leads to false acceptance. In this research the footprint biometric is used for identification of children. Most of the work done in literature is in verification mode. In this paper biometric identification is performed which will be helpful in finding the missing children. The database of 50 children's footprint is collected. The age of the children is 1 month to 5 years. Two types of input images are compared to achieve high accuracy. First input images are obtained by pre-processing and Region of Interest (ROI) extraction of the crease pattern from footprint images. Second are obtained by texture-based enhancement of crease pattern's ROI. Both the inputs are compared using state-of-the-art techniques and modern deep learning algorithms. The deep learning algorithm with enhanced crease patterns is giving 100 % accuracy, which is higher than the literature.","PeriodicalId":224655,"journal":{"name":"7th International Conference on Computing in Engineering & Technology (ICCET 2022)","volume":"55 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117277276","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":"Design and analysis of broadband WDM system for 5G and beyond","authors":"D. Jain, B. Iyer","doi":"10.1049/icp.2022.0624","DOIUrl":"https://doi.org/10.1049/icp.2022.0624","url":null,"abstract":"Demand for large bandwidth is increasing day by day due to the extensive usage of the internet, various gaming applications, and mobile communication. Optical fibers fulfill this requirement because it has enormous bandwidth. In the present article, we have designed a wideband WDM system, which operates in E, S, C, and L bands, over a bandwidth of 29.509 THz (or 273 nm). In the proposed wideband WDM system, the four channels operated at 1427 nm (E band), 1520 nm (S-band), 1550 nm(C band), and 1600 nm (L band). The data rate used was 40 Gbps. The system is analyzed by varying the fiber length from 25 km to 125 km and laser power from −5 dBm to 10 dBm. The system's performance is evaluated by BER, quality factor, output optical power, and eye diagram. We successfully demonstrated that at −5 dBm/100km, the quality factor and BER as 9.39, 9.16, 10.20, 6.76 and 2.80 ×10−21, 2.32×10−20, 9.45×10−25, 6.55×10−12. Similarly, at 10 dBm/125km the Q factor and bit error rate was 5.13, 24.32, 16.18, 7.64 and 1.36×10−07, 5.39×10−131, 2.99×10−59, 1.05×10−14 for 10 dBm for the four channels respectively. The proposed wideband WDM system was designed and simulated using optisystem 13.","PeriodicalId":224655,"journal":{"name":"7th International Conference on Computing in Engineering & Technology (ICCET 2022)","volume":"122 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115464040","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":"An improved DFT spread with genetic algorithm in layered PTS for reduced PAPR in FBMC OQAM systems","authors":"K. Ayappasamy, G. Nagarajan, P. Arunagiri","doi":"10.1049/icp.2022.0625","DOIUrl":"https://doi.org/10.1049/icp.2022.0625","url":null,"abstract":"The Partial Transmit Sequence (PTS) is the innovative method for low Peak to Average Power Ratio (PAPR) in multicarrier modulations (MCM). The Filter Bank Multi-carrier (FBMC) method proves a promising technique in advanced wireless communication. The addition of the cyclic prefix reduces the interferences that cause spectral efficiency degradation. Also, computational complexity is the major problem in MCM. It is anticipated to use a Genetic Algorithm (GA) and improve DFT spread in a layered partial transmit sequence (GA-LPTS). The projected system endures splitting each subblock, renovating the conventional PTS's one-layer structure into a dual-layer phase rotation factors search arrangement, and introducing a consequence-related threshold point. The GA then obtains the suboptimal phase factor vectors before PAPR reduction processing. The DFT spread IGA-LPTS scheme successfully condenses the FBMC/OQAM signal's PAPR. The anticipated results are compared to those obtained using the penalty concave-convex procedure (penalty-CCCP) and the carrier frequency offset (CFO) algorithm.","PeriodicalId":224655,"journal":{"name":"7th International Conference on Computing in Engineering & Technology (ICCET 2022)","volume":"44 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132584864","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}