S. Shilaskar, Rahul Ekambaram, Rugved Rajandekar, Ritika Sisodiya
{"title":"Computer Vision based Activity Recognition: Studying and Chit chatting","authors":"S. Shilaskar, Rahul Ekambaram, Rugved Rajandekar, Ritika Sisodiya","doi":"10.1109/INOCON57975.2023.10101091","DOIUrl":"https://doi.org/10.1109/INOCON57975.2023.10101091","url":null,"abstract":"In a tech-driven and automated world, it is no surprise that innovation and research are reaching new heights and one such progress that has been researched, falls in the domain of image recognition, that is, Human Activity Recognition (HAR). Recent studies have shown their interest in human activity recognition systems that use computer vision and various machine learning algorithms to classify an image into different activities over which the model has been trained. A detailed review of many existing similar literature works that follow the CV-based projects for recognition purposes was also referred. This paper mainly focuses on activity recognition of studying and chitchat activities. The proposed method for HAR is purely CV based which uses a dataset of 2400 images, equally divided into two different activities, containing 1200 per activity. This work will be beneficial in recognizing human behavior, in surveillance and assisted living, elder care, and healthcare monitoring systems along with trending research areas such as human-robot interactions as well as gaming and entertainment. The best results were showcased by the KNN classifier after using the BRISK feature detector achieving an overall accuracy of 78 percent.","PeriodicalId":113637,"journal":{"name":"2023 2nd International Conference for Innovation in Technology (INOCON)","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128514825","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":"Developing of NPA predictive Model for Pawning Advances in Sri Lankan Banking Industry","authors":"Nishadi Bamunuarachchi, Chameera De Silva","doi":"10.1109/INOCON57975.2023.10101183","DOIUrl":"https://doi.org/10.1109/INOCON57975.2023.10101183","url":null,"abstract":"The banking sector in Sri Lanka has been a major contributor to its profitability since the regulation of pawning in 1942 and its commencement in banks in 1961. The business of pawning has been influenced by global economic events such as the 2008 financial crisis and the subsequent increase in gold prices. However, with falling global inflation and a decrease in gold prices in 2013, the risk of nonperforming loans in the pawning and gold-backed loan segments increased for Sri Lankan banks. Four models were developed to evaluate the performance of the pawning business and the best models were found to be M1 (PCA with six features and SVM) and M3 (RFECV feature elimination with Logistic Regression), both with accuracy scores of 95% and 96% respectively. It was observed that RFECV selected all 10 features in the dataset.","PeriodicalId":113637,"journal":{"name":"2023 2nd International Conference for Innovation in Technology (INOCON)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124630317","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 Low Power APB with an Area Efficient Structure","authors":"Silpakesav Velagaleti","doi":"10.1109/INOCON57975.2023.10100979","DOIUrl":"https://doi.org/10.1109/INOCON57975.2023.10100979","url":null,"abstract":"This paper objective is to introduce an AMBAAPB (Advanced Microcontroller Bus Architecture-Advance Outer Bus) Bridge for the robust positioning of gadget objects. In order to achieve this, a simulation and synthesis of the bridge interface has been designed, which can be efficient in terms of energy usage as well as space utilization. APB Bridge is also compared with and without data security. The results show the effective utilization of area and power by the APB-Bridge with data security when compared with APB-Bridge without data security. The data is made secure using LFSR.","PeriodicalId":113637,"journal":{"name":"2023 2nd International Conference for Innovation in Technology (INOCON)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124640900","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}
D. Nagajyothi, Shaik Ashik Ali, V. Jyothi, Praharsha Chinthapalli
{"title":"Intelligent Waste Segregation Technique Using CNN","authors":"D. Nagajyothi, Shaik Ashik Ali, V. Jyothi, Praharsha Chinthapalli","doi":"10.1109/INOCON57975.2023.10101021","DOIUrl":"https://doi.org/10.1109/INOCON57975.2023.10101021","url":null,"abstract":"One of the main issues facing recycling systems in our country’s big cities is waste segregation. 62 million tons of trash are produced annually in India. Plastic garbage makes for 5.6 million tons of this total. Every year, this is recycled to a degree of around 60%. There are also 11.9 million tonnes of 43 million tonnes of solid garbage were recycled. Despite the figures sound wonderful, but the segregation of recyclable materials is a major issue in the recycling sector. prior to recycling or other trash management methods. In India, Currently, when garbage is collected from residences, it is not separated. So to sort this garbage, a large crew and much effort are required.Additionally, because to the presence of harmful compounds in the trash, those employed in this sector are vulnerable to a number of illnesses. Therefore, the goal is to increase productivity while reducing human interaction in the waste sorting process. The proposed study aims to develop a convolutional neural network-based image classifier that can recognize objects and determine the sort of garbage they contain. In this study, the model VGG16 was used to extract characteristics from photos, input them into a classifier, and generate predictions about how to tell one sort of garbage from another. In India, pollution from municipal solid waste has long been an issue. Every minute, garbage is produced by people. Solid waste management is made more challenging by ineffective waste segregation. Waste segregation may be facilitated and improved with computer vision. In order to categorize the waste categories of 8069 photos of municipal solid trash, the model uses CNN-based waste-type classifiers (VGG-16). The model will investigate how well four CNN architectures categorize wastes.","PeriodicalId":113637,"journal":{"name":"2023 2nd International Conference for Innovation in Technology (INOCON)","volume":"73 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124700449","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":"UAV Information Detection and Processing System Based on DTN algorithm","authors":"Liping Wu, Xiaobing Liao","doi":"10.1109/INOCON57975.2023.10101076","DOIUrl":"https://doi.org/10.1109/INOCON57975.2023.10101076","url":null,"abstract":"Based on the movement characteristics of UAV network nodes and the mobile model of aviation self-organized network nodes, this paper improves the model deceleration process and the transition relationship between different operating states. On the basis of the improved mobile model, a node link connection prediction method based on hidden Markov model is proposed. The topology model of satellite and UAV hybrid network is built by using the updated discrete graph, and the connection probability is introduced. Through simulation, TMDR can achieve the minimum transmission delay when meeting the constraint task requirements, which verifies the feasibility of data transmission based on the updated discrete graph.","PeriodicalId":113637,"journal":{"name":"2023 2nd International Conference for Innovation in Technology (INOCON)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130409359","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 Study To Detect Emotions From Twitter Text Using Machine Learning Algorithms","authors":"Anusha, Savitha A Shenoy, S. Harish","doi":"10.1109/INOCON57975.2023.10101258","DOIUrl":"https://doi.org/10.1109/INOCON57975.2023.10101258","url":null,"abstract":"One of the main factor contributing to mental illness, which has been linked to an increased risk of dying young is depression. Additionally, it significantly contributes to suicide ideation. Although there are many underlying reasons of depression, social networking sites play a key part in raising the likelihood of depression. In recent years social media has become the integral part of our daily lives. User reflects his internal life in the content he shares in his social media platform like twitter. People share happy incidents, joyful memories and sad moments through tweets. Thus it is possible to forecast depression in people using Twitter data. Various machine learning techniques have been employed to analyze these data. The algorithms employed are Naïve Bayes and Logistic Regression. Those algorithms will produce intended outcomes.","PeriodicalId":113637,"journal":{"name":"2023 2nd International Conference for Innovation in Technology (INOCON)","volume":"58 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126673410","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}
B. B. Dash, Utpal Chandra De, Trupti Mayee Behera, Tapaswini Samant, Shobhan Banerjee
{"title":"Recommendation System for E-Commerce Apparel Stores based on Text-Semantics","authors":"B. B. Dash, Utpal Chandra De, Trupti Mayee Behera, Tapaswini Samant, Shobhan Banerjee","doi":"10.1109/INOCON57975.2023.10101358","DOIUrl":"https://doi.org/10.1109/INOCON57975.2023.10101358","url":null,"abstract":"For physical offline stores as association analysis plays an important role in the maximization of sales, similarly, for online E-Commerce stores recommendation systems play a major role to enhance the shopping experience of users by suggesting similar kinds of products based on past search history. Just a single search for a product is sufficient to flood the social media and emails of users with various similar products in the form of advertisements, promotional videos & other posts. In this paper, we have discussed a recommendation system using text-semantics-based methods for ladies’ Apparel and finally, a comparative analysis has been done with our previous works on this aspect.","PeriodicalId":113637,"journal":{"name":"2023 2nd International Conference for Innovation in Technology (INOCON)","volume":"124 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116315658","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":"Fraudulence Detection of Medical Images using Pixel Level Algorithm","authors":"Thigulla Amulya Goud, G. Satish Kumar, Vanam Madhu Shalini, B.Abhilash Goud","doi":"10.1109/INOCON57975.2023.10101217","DOIUrl":"https://doi.org/10.1109/INOCON57975.2023.10101217","url":null,"abstract":"Healthcare is one of the important, sensitive and superior department for a country. While the healthcare sector is developing, security and privacy becomes our major concern. Trust between the doctor and patient is the major foundation in medical field. This type of fraudulence may put that trust at risk by providing wrong treatment on the basis of the forged images. Technologies like these makes the job easier, establish strong trust and secure client’s dignity. Our project gives a system of fraudulence detection of medical images for the healthcare department to verify that images related to health are not tampered, changed or altered. In our model we used the Hybrid Median-filter-based noise reduction technique. Our model constitutes SVM+ELM classifiers and their combined result is subjected to Bayesian sum rule and whether fraudulence is involved or not is decided.","PeriodicalId":113637,"journal":{"name":"2023 2nd International Conference for Innovation in Technology (INOCON)","volume":"42 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121544096","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":"Transmission Line Fault Diagnosis and Location System in Distribution Network Based on PSO","authors":"Jia Qin, Hongbo Chu, Daquan Yu","doi":"10.1109/INOCON57975.2023.10101049","DOIUrl":"https://doi.org/10.1109/INOCON57975.2023.10101049","url":null,"abstract":"In this paper, Particle Swarm optimization (PSO) algorithm is used for active distribution network fault location. However, the PSO algorithm has the first defect. Therefore, this paper proposes an improved PSO algorithm based on the Taurus whisker search algorithm. Firstly, the algorithm uses the longicorn whisker search algorithm to improve the initial population quality of particle swarm optimization; Secondly, the relevant mathematical model of active distribution network fault location is established. Finally, based on the IEEE33-bus distribution network model, simulation experiments are carried out for single fault, multiple fault and information misinformation. The experimental results show that the BPSO algorithm can quickly and accurately locate the fault section.","PeriodicalId":113637,"journal":{"name":"2023 2nd International Conference for Innovation in Technology (INOCON)","volume":"61 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124132364","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":"Imposter detection with canvas and WebGL using Machine learning.","authors":"Manduti Sai Prathima, S. P. Milena, Pramila Rm","doi":"10.1109/INOCON57975.2023.10101070","DOIUrl":"https://doi.org/10.1109/INOCON57975.2023.10101070","url":null,"abstract":"Authentication offers a way to confirm the legitimacy of a user attempting to access any protected information that is hosted on the web as organizations are moving their applications online. It has long been believed that IP addresses and Cookies are the most reliable digital fingerprints used to authenticate and track people online. But after a while, things got out of hand when modern web technologies allowed interested organizations to use new ways to identify and track users. There are many new reliable digital fingerprints that can be used such as canvas and WebGL. The canvas and WebGL render the image which is dependent on the software and hardware of the system. In our work with the generated hash value value from canvas and WebGL we create a model using KNN to identify the imposters. The model has proved to be accurate in authentication of user with an accuracy of 89%.","PeriodicalId":113637,"journal":{"name":"2023 2nd International Conference for Innovation in Technology (INOCON)","volume":"98 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127671749","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}