{"title":"An Optimized Object Detection System using You Only Look Once Algorithm and Compare with Deep Neural Networks with increased","authors":"Arun Kumar Reddy Padala, P. Malathi","doi":"10.1109/ICSCDS53736.2022.9760988","DOIUrl":"https://doi.org/10.1109/ICSCDS53736.2022.9760988","url":null,"abstract":"The main objective of this research is to detect and track and recognize objects of different sizes using the novel you only look once algorithm and compare its accuracy with deep neural networks. Various kinds of objects are detected, recognized and tracked using the Novel You Only Look Once algorithm ($mathrm{N}=10$) and its accuracy is compared with deep neural networks ($mathrm{N}=10$) algorithm. In the research, the proposed algorithm i.e, the Novel You Only Look Once algorithm and Deep Neural networks techniques are utilized and the accuracy between those techniques are analysed. The accuracy of Deep Neural Networks is about 89.18% and using the Novel You Only Look Once algorithm is 97.48% with ($mathrm{p} < 0.005$). Upon researching, studying various thesis and books and inferring results, it was proved that the novel you only look once algorithm has a greater accuracy than deep neural networks.","PeriodicalId":433549,"journal":{"name":"2022 International Conference on Sustainable Computing and Data Communication Systems (ICSCDS)","volume":"41 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-04-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122372522","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}
A. Musthafa, M. Ambika, Abinaya Kn, Dharshini M, I. M, P. R.
{"title":"Oryza Sativa Leaf Disease Detection using Transfer Learning","authors":"A. Musthafa, M. Ambika, Abinaya Kn, Dharshini M, I. M, P. R.","doi":"10.1109/ICSCDS53736.2022.9760972","DOIUrl":"https://doi.org/10.1109/ICSCDS53736.2022.9760972","url":null,"abstract":"Oryza sativa (Rice) is the world's most significant cereal harvest. It is taken as a staple feast for energy by the greater part of the total populace. Abiotic and biotic components like precipitation, soil richness, temperature, bugs, microscopic organisms, infections, etc. impact the yield creation amount and nature of rice grain. Ranchers contribute a great deal of time and energy to infection prevention, and they recognize sicknesses with their devastated unaided eye technique, which prompts unfortunate cultivating. The advancement of horticultural innovation helps significantly supports the computerized location of pathogenic living beings in the leaves of rice plants. The convolutional-based neural network calculation (CNN) is the one of very profound calculations that has been effectively used to settle PC vision issues like picture grouping, object division, picture investigation, etc. The proposed model boundaries have been tuned for the order work, and it has a great exactness of 95.67 percent. Using the transfer learning the data are trained faster andit can learn and apply the learned things in the next dataset faster. So that it does not acquire time in learning, which is not in the existing process.","PeriodicalId":433549,"journal":{"name":"2022 International Conference on Sustainable Computing and Data Communication Systems (ICSCDS)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-04-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130604509","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. Poonguzhali, S. F. Sowmiya, P. Surendar, M. Vasikaran
{"title":"Fake Reviews Detection using Support Vector Machine","authors":"R. Poonguzhali, S. F. Sowmiya, P. Surendar, M. Vasikaran","doi":"10.1109/ICSCDS53736.2022.9760747","DOIUrl":"https://doi.org/10.1109/ICSCDS53736.2022.9760747","url":null,"abstract":"One of the fastest expanding business categories in the world today is internet shopping. People nowadays buy a lot of things from internet shopping sites. Customers can buy a better quality products based on the reviews given by previous buyers of the products. Reviews includes text reviews, ratings and smileys. On a product review there are hundreds of reviews in which some of the reviews would be fake reviews. Opinion mining from natural languages is a difficult method for evaluating customers' sentiments, but sentiment analysis provides the best answer. It provides crucial data for decision-making in a variety of fields. So, we propose a fake reviews detection system using support vector machine which detect the fake reviews of the products. The primary goal is to suggest higher-quality products to the user. We use the support vector machine algorithm to classify the reviews into positive and negative groups. Finally fake reviews are predicted which are posted by the users. The reviews are grouped as negative, positive and neutral. In this system, only purchased users can post the reviews and duplicates are verified based on user id and booking id. Genuine reviews are considered for product recommendation","PeriodicalId":433549,"journal":{"name":"2022 International Conference on Sustainable Computing and Data Communication Systems (ICSCDS)","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-04-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130612351","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 Analysis of Face Liveness Detection Mechanisms via Deep Learning Models","authors":"Syed Zoofa Rufai, A. Selwal, Deepika Sharma","doi":"10.1109/ICSCDS53736.2022.9760922","DOIUrl":"https://doi.org/10.1109/ICSCDS53736.2022.9760922","url":null,"abstract":"In recent times, susceptibility of face recognition system to spoofing attacks has received a significant attention from research community. These attacks simply involve presenting an artifact (i.e., video replay, print photo or fabricated mask)to the sensor component and have shown to be capable of deceiving face recognition (FR) systems. The design of an anti-deception method that is termed as face spoof detector is a challenging task that aims to reveal a fake user seeking to mislead the verification system. In this study, we present an analysis of state-of-the-art face spoofing attack discernment techniques along with a taxonomy. A focused survey of face anti-spoofing via deep learning-based methods with special emphasis on latest trends in deep learning techniques is expounded. Additionally, a comparative summary of benchmark face-anti-spoofing datasets employed for various data-driven models is also illustrated. We offer a brief overview of various evaluation protocols for measuring the effectiveness of FASDD approaches. The presented study investigates several key challenges that are open to researchers for further progression in this active field of FLD. Our analysis clearly advocates that among all, accuracy of FLD algorithms in cross-material scenario is still a challenging task. The training overhead of deep convolutional neural networks (CNN) deployed as anti-spoofing detectors demonstrates comparatively better accuracy with an additional training overhead.","PeriodicalId":433549,"journal":{"name":"2022 International Conference on Sustainable Computing and Data Communication Systems (ICSCDS)","volume":"65 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-04-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130628888","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":"Interactive Audio Indexing and Speech Recognition based Navigation Assist Tool for Tutoring Videos","authors":"Gareshma N, V. P, P. S","doi":"10.1109/ICSCDS53736.2022.9760784","DOIUrl":"https://doi.org/10.1109/ICSCDS53736.2022.9760784","url":null,"abstract":"The volume of worldwide multimedia data increases daily, especially the growth and usage is enormus during the pandemic period. Content-based audio retrieval increases the sophistication in the usage of multimedia content. While listening to the multimedia, the user navigates to the desired location, either manually or with subtitles. Both these methods are time-consuming and not user friendly. To address this issue, we have developed a speech-based searchable system that transcribes the video material to text and allows the user to navigate to the desired content. The user may listen to video lectures and guides to the topic of interest with the voice command. The system analyses the acoustic signature of the input voice command and matches it against the video. The proposed system maintains the index table, which maps the transcription of the content with the instance of the occurrence. The interactive play control retrieves the instance of the keyword and plays the multimedia content from that instant. The combination of effective transcription, storage and retrieval complements the system and improves the ease of access.","PeriodicalId":433549,"journal":{"name":"2022 International Conference on Sustainable Computing and Data Communication Systems (ICSCDS)","volume":"44 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-04-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132076003","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 Efficient ResNet-50 based Intelligent Deep Learning Model to Predict Pneumonia from Medical Images","authors":"Mohit Chhabra, Rajneesh Kumar","doi":"10.1109/ICSCDS53736.2022.9760995","DOIUrl":"https://doi.org/10.1109/ICSCDS53736.2022.9760995","url":null,"abstract":"Pneumonia is a devastating disease from which millions of people died every year. Deep learning can be considered as a crucial tool for detecting the disease quickly and accurately. For diagnosis purpose computer assisted methods are less accurate and outdated. So Deep learning is considered as a better option as compared to traditional methods. In this research work, the authors have proposed an efficient ResNet-50 Transfer learning-based Convolutional Neural Network Model to predict pneumonia using medical images. Kaggle based open source dataset repository is used for the experimental analysis. Techniques such as data augmentation, fine tuning, residual blocks, and transfer learning had been used for the better results in terms of maximizing accuracy and minimizing loss. After applying the deep learning methods, the authors achieved an accuracy of 96.6% which is better as compared to other recent literature work. Results shows that this model provided better accuracy and also can be used as a screening test for prediction of pneumonia diagnosis.","PeriodicalId":433549,"journal":{"name":"2022 International Conference on Sustainable Computing and Data Communication Systems (ICSCDS)","volume":"43 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-04-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130934752","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}
A. Pawar, Pranav Gawali, Mangesh Gite, M. A. Jawale, P. William
{"title":"Challenges for Hate Speech Recognition System: Approach based on Solution","authors":"A. Pawar, Pranav Gawali, Mangesh Gite, M. A. Jawale, P. William","doi":"10.1109/ICSCDS53736.2022.9760739","DOIUrl":"https://doi.org/10.1109/ICSCDS53736.2022.9760739","url":null,"abstract":"Hate speech spreads as the quantity of content on the internet grows. Automated methods for identifying hate speech in text face a number of challenges, which we investigate and assess. Language complexity, differing views on what constitutes hate speech, and data availability restrictions for algorithm training and testing are some of the difficulties. As a result, it may be difficult to decipher the reasoning behind the decisions made by many current methods. With our multiview SVM technique, we give near-state of the art SVM results that are easier to comprehend than neural approaches. In addition, we look at the challenges that this endeavour faces on a technological and practical level.","PeriodicalId":433549,"journal":{"name":"2022 International Conference on Sustainable Computing and Data Communication Systems (ICSCDS)","volume":"106 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-04-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130964498","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":"Construction of Application Scenarios of Computer Network and 6G Network in Electronic Information Engineering","authors":"Zeming Xiong","doi":"10.1109/ICSCDS53736.2022.9761020","DOIUrl":"https://doi.org/10.1109/ICSCDS53736.2022.9761020","url":null,"abstract":"This article mainly analyzes the application scenarios of computer network and 6G network in electronic information engineering. This article briefly analyzes the practice of computer network technology in electronic information engineering, and puts forward some application suggestions. The progress of the engineering industry contributes to its strength. In the 6G era, endogenous intelligence is expected to be formed. However, most of the current research focuses on artificial intelligence-based transmission and network optimization methods, and seldom discusses how to efficiently support the implementation of artificial intelligence methods at the architecture design level.","PeriodicalId":433549,"journal":{"name":"2022 International Conference on Sustainable Computing and Data Communication Systems (ICSCDS)","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-04-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130381956","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}
Y. H. Robinson, R. Krishnan, K. Narayanan, A. Sangeetha, I. Sakthidevi, J. Raj
{"title":"Secured Energy Proficient and Clustering Methodology for Wireless Sensor Networks","authors":"Y. H. Robinson, R. Krishnan, K. Narayanan, A. Sangeetha, I. Sakthidevi, J. Raj","doi":"10.1109/ICSCDS53736.2022.9760941","DOIUrl":"https://doi.org/10.1109/ICSCDS53736.2022.9760941","url":null,"abstract":"The secured communication and proficient energy utilization are the common challenges for providing effective routing in Wireless Sensor Networks (WSNs). The WSN is constructed through the effective network framework which has the nodes with dissimilar data processing, communication capability. The data collection and effective clustering process can utilize the grouping of sensor nodes and reducing the routing overhead. The Secured Energy Proficient and Clustering methodology (SEPC) is proposed in this paper for determining the efficient clustering transmission of data packets into the base station, the main contribution of this technique is enhancing the energy utilization and network security in effective manner. The performance analysis proves that the proposed technique is provided enhanced results than other techniques in terms of throughput, reliability, energy utilization, packet delivery ratio, and end-to-end delay.","PeriodicalId":433549,"journal":{"name":"2022 International Conference on Sustainable Computing and Data Communication Systems (ICSCDS)","volume":"77 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-04-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125522161","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":"Research on Network Intelligent Finance Data Mining and Analysis System and Quantitative Model","authors":"Yaling Chen, Zhengdong Hu","doi":"10.1109/ICSCDS53736.2022.9760740","DOIUrl":"https://doi.org/10.1109/ICSCDS53736.2022.9760740","url":null,"abstract":"Based on time series data mining, this paper studies financial data analysis systems and quantitative models to improve the service quality of financial data, improve the management efficiency of financial data, and provide financial data managers with more convenient services. When the financial data analysis system was designed, the system was divided into six modules: data collection and update function, financial consulting information management function, financial risk control management function, intelligent mining and analysis function, financial data monitoring function, and stock correlation comparison function. Among them, a data mining risk control model based on time series is established during intelligent mining. In this paper, the method of financial data prediction uses the long and short time memory algorithm.","PeriodicalId":433549,"journal":{"name":"2022 International Conference on Sustainable Computing and Data Communication Systems (ICSCDS)","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-04-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125584221","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}