2022 5th International Conference on Advances in Science and Technology (ICAST)最新文献

{"title":"Evolution and Testimony of Deep Learning Algorithm for Diabetic Retinopathy Detection","authors":"Pranali Hatode, Maniroja M Edinburgh, Martand Jha","doi":"10.1109/ICAST55766.2022.10039538","DOIUrl":"https://doi.org/10.1109/ICAST55766.2022.10039538","url":null,"abstract":"A deep neural network (DNN) is an artificial neural network (ANN) with various layers incorporated between the input and output layers. Deep Neural Networks (DNNs) embodies such a type of network where each and every respective layer performs convoluted functions such as demonstration and conceptualization that comprehend images, sound and text. Deep learning functions along with artificial neural networks, these networks are well suited for imitating how humans contemplate and learn. DL mainly consists of analyzing, learning and improving on its own by inspecting computer algorithms. Image classification, language translation, and speech recognition has been supported by deep neural networks. Without human involvement, deep neural networks can resolve any pattern recognition problem. This paper, focuses on the growth and confirmation of a deep Learning algorithm for early-stage diabetic retinopathy detection. Diabetic Retinopathy, a disorder that crops up in the human eye, if not treated at an early stage, may lead to blindness by lesions on the retina. Hence, ResNet 50 a deep learning technique is presented to automate the recognition of the diabetic retinopathy images by the classification of retinal fundus images from kaggle database. Over 3662 images which are retinal fundus images are used for training and validation. The accuracy achieved after first epoch is 90.74% and after final epoch 91.60%.","PeriodicalId":225239,"journal":{"name":"2022 5th International Conference on Advances in Science and Technology (ICAST)","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127364701","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 Vision Transformer Approach for Classification an A Small-Sized Medical Image Dataset","authors":"Dhruvin Gandhi, Vaishnavi Shah, P. Chawan","doi":"10.1109/ICAST55766.2022.10039593","DOIUrl":"https://doi.org/10.1109/ICAST55766.2022.10039593","url":null,"abstract":"In natural language processing, transformers have supplanted RNN models as more advanced technology. The vision transformer (ViT) model which is built upon the transformer architecture brought the concept of self-attention to images. Though the ViT model has given a better performance than CNNs on huge datasets, it still gives a poor performance on small-sized datasets when trained from scratch. This is because of its low locality inductive bias problem. This paper proposes a modified vision transformer architecture that would consist of three additional layers. A modified tokenization layer, a token learner layer, and a stochastic depth layer. The model is trained from scratch on a small-sized medical image dataset which is HAMS10000. The model is then compared with inception ResNet V2, a Vgg16 model, and a conventional ViT model trained on the same dataset. We see a more than 10% improvement in the ViT model and a significant increase in accuracy compared to the CNN models.","PeriodicalId":225239,"journal":{"name":"2022 5th International Conference on Advances in Science and Technology (ICAST)","volume":"54 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125306829","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":"Slot Loaded Circular Microstrip Antenna for Circular Polarized Response","authors":"A. Ambekar, Tejal Page, Venkata A. P. Chavali, A. Deshmukh","doi":"10.1109/ICAST55766.2022.10039647","DOIUrl":"https://doi.org/10.1109/ICAST55766.2022.10039647","url":null,"abstract":"A circular microstrip antenna embedded through an e-shape slot is stated for a circular polarized response. The projected antenna shows an overall gain improvement of more than 5 dBi over the bandwidth, an impedance bandwidth of 75 MHz, and an AR bandwidth of 40 MHz. The said work lacks a detailed analysis of resonant modes that produce the circular polarized response. Also, the structure complexity increases due to the use of an e-shape slot moreover the cost increases owing to the use of RO4003 for fabrication. The present paper gives the alternative simple structure for realizing circular polarized response using a circular microstrip antenna embedded with a simple circular slot fabricated on Arlon substrate. Identifications of patch modes are supported by in-depth parametric analysis. The proposed low profile cost-effective antenna is simple in structure and yields a VSWR bandwidth of 45 MHz, AR bandwidth of 15 MHz with an inclusive gain of greater than 4.5 dBi over the impedance bandwidth","PeriodicalId":225239,"journal":{"name":"2022 5th International Conference on Advances in Science and Technology (ICAST)","volume":"38 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115465572","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":"COVID-19 Risk Prediction and Contact Tracing","authors":"Sunayana V Jadhav, A. Shaikh, Hassaan Khan, Saket Uchil, Darshi Sejpal","doi":"10.1109/ICAST55766.2022.10039568","DOIUrl":"https://doi.org/10.1109/ICAST55766.2022.10039568","url":null,"abstract":"The emergence of the coronavirus COVID- 19 switched the limelight onto digital health technologies. To help the infection rates from surging, numerous governments are looking into applications that could help disrupt infection chains beforehand. We created a Self-Assessment Test using COVID Symptoms, that's capable of assessing the threat of COVID- 19 in the user using ML. The data also tracks the user and gives safety tips and recommendations. Using the Track Module, the user is notified of the nearby containment zones. The contact tracing module helps the user to maintain a specified distance from others.","PeriodicalId":225239,"journal":{"name":"2022 5th International Conference on Advances in Science and Technology (ICAST)","volume":"53 25","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"113933817","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 Review: A Blockchain based Crowdfunding Decentralized Application","authors":"Dhiraj Parmar, Paras Kori, Omkar Singh Chauhan, Jyoti Wadmare","doi":"10.1109/ICAST55766.2022.10039601","DOIUrl":"https://doi.org/10.1109/ICAST55766.2022.10039601","url":null,"abstract":"Raising funds before starting new initiatives or entrepreneurial ventures is without a doubt the most challenging task. Also, rampant frauds in crowdfunding gives rise to doubt in the concept of crowdfunding. Traditionally, crowdfunding was the key to the success of many start-ups and ventures. But with increasing competition and swindling of data it was a necessity to develop a system which assured the investors, venture capitalists and individuals a stress-free experience in investing and continuing the legacy of supporting new ideas and their creators. Thus, blockchain technology is a one stop solution for our problem. Blockchain provides us a decentralized, permissionless and secured environment. In this paper we introduce an enhanced version of Ethereum based crowdfunding for raising funds for path breaking projects and ideas. The main goal is to develop a smart contract that will enable investors to contribute to innovative ideas in a secure manner with a guarantee of the money.","PeriodicalId":225239,"journal":{"name":"2022 5th International Conference on Advances in Science and Technology (ICAST)","volume":"204 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121619864","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":"Classification and Analysis of Distributed Denial of Service Attacks using Machine Learning Techniques","authors":"P. Nandhini, S. Kuppuswami, C. Abinaya, R.B. Boomika, N. Deepthi","doi":"10.1109/ICAST55766.2022.10039565","DOIUrl":"https://doi.org/10.1109/ICAST55766.2022.10039565","url":null,"abstract":"According to the recent statistics, DDoS attacks are responsible for the majority of overall network attacks. A distributed denial of service attack, sometimes known as a DDoS attack will destroy the server system resources such as the CPU, control and memory. As a result, the server will be too busy responding to a DDoS attack to provide service to the genuine users. Networks struggle to discern between malicious and lawful transmissions. Due to numerous variables like the rigidity, complexity and networking equipment, testing and deploying DDoS methods is difficult. Machine Learning are used to detect the DDoS attack but the best ML model to classify the DDoS attack is yet to be found. The proposed system makes use of supervised learning algorithm to find out the model that best classifies the DDoS attacks. Performance metrices have been calculated for various models. To ensure its suitability, the result was also compared with those from other models. As a result, accuracy of more than 96 percent have been achieved using Random Forest algorithm.","PeriodicalId":225239,"journal":{"name":"2022 5th International Conference on Advances in Science and Technology (ICAST)","volume":"410 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126689504","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":"Embracing Permissioned Blockchain for a Secure and Reliable Land Registration System","authors":"Y. Borse, Purnima Ahirao, A. Chawathe, D. Patole","doi":"10.1109/ICAST55766.2022.10039485","DOIUrl":"https://doi.org/10.1109/ICAST55766.2022.10039485","url":null,"abstract":"Digitization of Land Registry System has been in the initial phases of implementation in various countries all over the world. Especially in India, the existing land recording system is vulnerable and prone to manipulation. The key issues associated with the land registration and management are first lack of transparency in recordkeeping (among government official involved as well as the related private individual), second time consuming (verify or access the information takes time), the slow processing brought on by the numerous officials involved in the process, and the lack of required data availability on their end (such as inconsistent, incomplete, or out-of-date data). In this paper, authors tried to embrace the features of blockchain technology to tackle these issues without hampering or eliminating the mandatory government official's roles. The permissioned blockchain, Hyperledger Fabric is used to implement the proposed system. The roles like and Sub-registrar offices are regarded as government officials and are required to conform to the land title registration policy. The Hyperledger chain codes are used to enforced the requirement and provide a hassle-free land registration and management process.","PeriodicalId":225239,"journal":{"name":"2022 5th International Conference on Advances in Science and Technology (ICAST)","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126751293","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":"Mood Indicator: Music and Movie Recommendation System using Facial Emotions","authors":"Sanjay M. Vidhani, Freya Vora, Jainam Chhadwa, Arya Karambelkar, Param Mamania","doi":"10.1109/ICAST55766.2022.10039649","DOIUrl":"https://doi.org/10.1109/ICAST55766.2022.10039649","url":null,"abstract":"Everyone strives for success in today's world, however many people suffer from unhappiness as a result of this constant battle.Facial emotion recognition technology has been given a lot of scope and interest by the society and is being used in many industrieslike security systems, DVP, and other technical breakthroughs.Mood Indicator was developed to help people in recommending films and tunes based on their emotions.60% of users say that the number of songs or videos in their collection is so big that they can't pick which to play.By creating a recommendation system, we can help a user in deciding which entertainment factor to listen to,which reduces the stress levels of the client. It is time efficient too.","PeriodicalId":225239,"journal":{"name":"2022 5th International Conference on Advances in Science and Technology (ICAST)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125908580","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":"Predicting Learning Behavior Using Hyper-Personalization and Attentiveness Measure","authors":"Rahil Desai, Riya Muni, Devanshi Madhani, Abhijit Joshi","doi":"10.1109/ICAST55766.2022.10039646","DOIUrl":"https://doi.org/10.1109/ICAST55766.2022.10039646","url":null,"abstract":"With advances in educational technology, the use of online courses and e-learning platforms has increased. However, the primary issue with online learning is that learners usually fail to complete the entire course. In addition, the instructor has no mechanism of knowing how diligently the learners complete the course and whether the course requires any refinement. Our proposed system addresses these concerns by using hyper-personalization, which aims to create a personalized curriculum for each learner based on their knowledge, areas of weakness, and interests. The customized curriculum development is accompanied by a feedback system that collects facial expressions and employs Convolutional Neural networks (CNN), Recurrent Neural networks (RNN), and other deep learning techniques to assess the learner's attentiveness during the course and determine whether they find the course interesting. This mechanism will assist the instructor in receiving appropriate input on the course, which will be useful for them to improve on the areas of concern. The proposed system thus designs a tailored curriculum for each learner and monitors their attentiveness to assist instructors with the course refinement.","PeriodicalId":225239,"journal":{"name":"2022 5th International Conference on Advances in Science and Technology (ICAST)","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133699067","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":"ESSCNN-automatic sleep apnea detection throughpre-trained ResNet50 using electrocardiogram signal","authors":"Nivedita Singh, R. H. Talvekar","doi":"10.1109/ICAST55766.2022.10039658","DOIUrl":"https://doi.org/10.1109/ICAST55766.2022.10039658","url":null,"abstract":"Sleep apnea (SA) is caused due to sudden drops in oxygen levels which create stress in the body. SA is increasingly common in our society. SA is characterized by airway collapse when we are sleeping which is chronic in nature. Most of the time people are unaware that, they are undergoing this disorder and thus remain undiagnosed. Untreated SA may be the consequence of high blood pressure, arrhythmia, cardiovascular diseases, strokes, and heart attack which is mortal ultimately. To detect SA most of the research work has already been done using polysomnography (PSG). We propose a novel method to detect and classify SA as normal, borderline, and apnea using a single-channel ECG signal in a pre-trained ResNet50 convolution neural network. In our research work, we have reported pre-trained convolution neural network (CNN) ResNet50 for classification using Physionet apnea ECG for training and testing and further, we have also investigated the robustness of the model in the University College Dublin (UCD) sleep apnea database. The different solvers adam, rmsprop, and sgdm, and two different learning rates 0.001 and 0.0001 are used to get the optimum result in pre-trained ResNet50 to diagnose SA. The detection of SA using our proposed novel method has achieved outstanding performance and achieved 100% accuracy for both the training and testing phase. Resnet50 is a high-accuracy model. Comparison of performance of the model in state-of-art training loss, and validation loss implemented on both physionet apnea ECG data and UCD apnea data. We conclude that all the trials are showing 100% accuracy but there is a difference in the training loss and validation loss. For learning rate 0.001 and adam solver the model is showing the least training loss as well as validation. Consequently, for learning rate 0.0001 and sgdm solver the model is showing the highest training loss as well as Figure 1. Block diagram and process flow diagram of the proposed system Figure 1. Block diagram and process flow diagram of the proposed system validation. The proposed model is highly accurate and efficient in classifying all three classes normal, apnea, and borderline subject. In future work, we plan to do performance optimization and hyperparameter tuning using various pre-trained architectures for SA detection and its characterization for determination of severity The training and testing both could be done in the graphics processing unit to improve the training and testing time.","PeriodicalId":225239,"journal":{"name":"2022 5th International Conference on Advances in Science and Technology (ICAST)","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114980801","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}