2022 First International Conference on Artificial Intelligence Trends and Pattern Recognition (ICAITPR)最新文献

{"title":"High Speed Multiplier using Embedded Approximate 4-2 Compressor for Image Multiplication","authors":"Thogiti Sai Aditya Teja, G. S. Teja, J. Ravindra, Lavanya Maddisetti","doi":"10.1109/ICAITPR51569.2022.9844191","DOIUrl":"https://doi.org/10.1109/ICAITPR51569.2022.9844191","url":null,"abstract":"Multiplication is the most widely used operation in a variety of applications such as digital filters and neural networks. In certain applications (image processing), precise computation is not required and, even low-accuracy computing can yield meaningful results. Since approximate computing is less complex and consumes less resources, it can be used in image processing and multimedia applications. Regular adders have a longer critical delay than compressor adders, making them suitable for use in multiplier architectures. Compressors can be employed in multiplication operations to reduce number of partial products, delay and power dissipation. We presented a 8×8 Dadda multiplier with an approximated 4:2 compressor in this research. On a pixel-by-pixel basis, this multiplier is used to multiply two images.","PeriodicalId":262409,"journal":{"name":"2022 First International Conference on Artificial Intelligence Trends and Pattern Recognition (ICAITPR)","volume":"77 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128641879","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":"Data Analysis of Electrical Systems Using Machine Learning Algorithms","authors":"Pillalamarri Madhavi, S. Satyanarayana","doi":"10.1109/ICAITPR51569.2022.9844178","DOIUrl":"https://doi.org/10.1109/ICAITPR51569.2022.9844178","url":null,"abstract":"Electrical Systems are designed in the amalgamation of various types of electrical equipment at the generation, transmission, and distribution verge to furnish uninterrupted power to the consumers. To communicate this process effectively, Machine learning techniques provide productive prediction and decision for any real-time application by using a set of instructions with proper statical data from the system. This paper gives a comprehensive study of Electrical Generation and Consumption through various sectors over the period of 2019-2020 and analyzes the prediction with regards to accuracy using various supervised Machine learning algorithms and conventional analysis of insulators for different voltage ratings.","PeriodicalId":262409,"journal":{"name":"2022 First International Conference on Artificial Intelligence Trends and Pattern Recognition (ICAITPR)","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134356005","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":"Fingerprint Classification using Deep learning","authors":"Sumaiya Ahmad, S. Jabin","doi":"10.1109/ICAITPR51569.2022.9844181","DOIUrl":"https://doi.org/10.1109/ICAITPR51569.2022.9844181","url":null,"abstract":"Biometrics are being extensively used in person authentication; while spoofing is used by the imposters to crack into the biometric systems. The paper deals with the fingerprint image classification into two classes viz. fake or genuine using Convolutional Neural Network (CNN) on ATVS-FFP dataset of fingerprint images of 17 users. The dataset is divided into two parts named as DS_WithCooperation and DS_WithoutCooperation, both the parts contain fake and original fingerprint images. These differ with respect to the acquisition of fake fingerprint which was done with and without the consent of the users. Thus, the fake fingerprint of latter part of the dataset were of low quality and represent the real-world scenario. The images were segmented to get the ridge region from the background noise using morphological image processing methods. The segmented images were then randomly rotated at different angles and were resized to 170X170X1. In this way the DS_WithCooperation resulted into 3264 images from a total of 816 fake and real images, similarly DS_WithoutCooperation resulted into 3072 images from a total of 768 fake and real images. This data set was then split in 3 to 1 ratio to form train and test datasets. For preparing the proposed model to classify fake and genuine images, CNN was trained using the Train data set. The model gave ACE (Average Classification Error) ranging from 0 to 2.45 on test datasets of both types with and without cooperation which is comparable to the state-of-the-art.","PeriodicalId":262409,"journal":{"name":"2022 First International Conference on Artificial Intelligence Trends and Pattern Recognition (ICAITPR)","volume":"409 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124343782","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":"Application of Blockchain in Healthcare","authors":"Akruti Sinha, Akshet Patel, Mukta Jagdish","doi":"10.1109/ICAITPR51569.2022.9844186","DOIUrl":"https://doi.org/10.1109/ICAITPR51569.2022.9844186","url":null,"abstract":"Blockchain appears to be the way of the future in today’s technological age. Blockchain technology has recently proven itself worthy of praise by facilitating cryptocurrency financial transactions. Despite being widely researched, there have recently been growing worries about the privacy and security of patient data because of the use of a centralized system to handle patient data. The General Data Protection Regulation (GDPR) grants the subject the right to know where and how his or her personal data is stored, as well as who is privy to it and to what extent. Blockchain has been shown in numerous studies to be capable of supporting the safe and secure recording of patient data in the health-care system. This paper summarizes recent research into how blockchain technology can be successfully implemented in the healthcare field. In our assessment of such publications, we discovered that the majority of blockchain applications are limited when only briefly examined. The products are only used by a small number of people. Perhaps this is due to the fact that healthcare blockchain applications have more demanding authentication, interoperability, and record sharing requirements. However, the quality of the products is constantly improving.","PeriodicalId":262409,"journal":{"name":"2022 First International Conference on Artificial Intelligence Trends and Pattern Recognition (ICAITPR)","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116345513","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 on Self Stabilizing Platform in Scope of Merchant Navy Applications","authors":"S. Vinod Kumar, M. Mahesh, K. Vinoth Kumar, Amarjeet Singh, Mohammed Omer Ali, Siddhartha Sunil Singh, Nayrah M A, Tahoora Imtiyaz, Umair Khan","doi":"10.1109/ICAITPR51569.2022.9844197","DOIUrl":"https://doi.org/10.1109/ICAITPR51569.2022.9844197","url":null,"abstract":"The advancement in robotics in the resent years has led to the integration of multiple disciplines of sciences to research and develop effective and reliable solutions for industries. This model is mainly focused on the Merchant navy industry where we have proposed the implementation if Self Stabilizing platform for various navy applications such as GLB/GLBE cranes, Helipads, etc. This model will be a 6 DoF/6 Axis model which is suitable for the movements for the scope of the applications proposed above. We have tried to fuse two different control methods for this model which are PID controller method and MEMS sensors methods which is a MUP6050 sensor. This model is better than the old mechanical link self-stabilizing platforms which are non-feedback control models. As the ship experiences storms the tilt in the bottom surface is detected and the upper platform tiles accordingly to maintain level and give stability to the GLB crane or the Helipad. This is a dynamic model which has real time active feedback.","PeriodicalId":262409,"journal":{"name":"2022 First International Conference on Artificial Intelligence Trends and Pattern Recognition (ICAITPR)","volume":"88 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126199102","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":"VLSI Implementation of a Energy Recovery 4-2 Compressor using PBL","authors":"S. Karunakaran, J. Vamshi, Chilkamarri Abhinav Reddy","doi":"10.1109/ICAITPR51569.2022.9844193","DOIUrl":"https://doi.org/10.1109/ICAITPR51569.2022.9844193","url":null,"abstract":"Approximate computing is employed in the image processing and multimedia applications since it is less difficult and consumes less power. Compressor outputs are estimated to construct estimated compressor. The scientific literature, which suggests a variety of circuits built with approximate 4-2 compressors, has created a lot of concern in approximation of multipliers. In exact compressors previously, emerged as a feasible solution for implementing approximate multipliers. In this project, we discovered that while keeping high speeds, it further decreases the power dissipation of approximation circuits using Pulse Boost Logic Method. We constructed a 4-2 compressor circuit employing to illustrate power savings and speed capabilities, using pulse boost logic. Cadence tool is used to run simulations with 45nm technology. At 800 MHz, our results reveal that a PBL-based approximation 4-2 compressor architecture saves 64% more power than a regular CMOS-based design. We also discussed how an accurate 4-2 compressor was designed using CMOS technology, combining approximation and ER computing can save 89% of power in a 4-2 compressor. We also mentioned that the suggested approximate 4-2 compressor based on PBL consumes 65% less energy than the existing one. Approximation 4-2 compressor is based on CMOS. The suggested 4-2 compressor with pulse boost logic-based approximation has been tested for functionality.","PeriodicalId":262409,"journal":{"name":"2022 First International Conference on Artificial Intelligence Trends and Pattern Recognition (ICAITPR)","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121970708","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":"Semi-Supervised Label Propagation Community Detection on Graphs with Graph Neural Network","authors":"S. Muppidi, Anupama Angadi, Satya Keerthi Gorripati","doi":"10.1109/ICAITPR51569.2022.9844211","DOIUrl":"https://doi.org/10.1109/ICAITPR51569.2022.9844211","url":null,"abstract":"The Graph Neural Network is a fairly innovative concept which permits neural networks to function on random graphs. As unbounded problem structures are universal in real-world scenarios and can be best denoted by graphs, Graph Neural Networks suggests new exhilarating applications and further simplified latent for machine learning wholly, but also noteworthy enhancement of performance in a deep learning domain. Graph Neural Networks are variant of Graph convolution networks can function sprightly on graphs. One of the well-known tasks attempted with this new skill is graph partitioning. Important characteristic of community is to discover graph nodes are with same interests and keep them strongly connected to extract groups for numerous reasons. We demonstrate a semi-supervised learning on graph data for solving community detection. In a number of trials on graph partitions we proved that our framework outperforms traditional ones.","PeriodicalId":262409,"journal":{"name":"2022 First International Conference on Artificial Intelligence Trends and Pattern Recognition (ICAITPR)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130261622","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":"Analysis of Customer Reviews using Deep Neural Network","authors":"Y. Lalitha, G. V. Reddy, K. Swapnika, Roshini Akunuri, Harshmeet Kaur Jahagirdar","doi":"10.1109/ICAITPR51569.2022.9844183","DOIUrl":"https://doi.org/10.1109/ICAITPR51569.2022.9844183","url":null,"abstract":"Customer Review Analysis has become a most important application of Businesses. This will enable the business to analyze the text data and know the sentiment of the customers on their business entities in the market. It requires a thorough computational study of the behavior of discrete entities with respect to customers purchasing affinity and extracting the customer’s point of view about the business entity. The business performance is always measured with customers satisfaction. In this era of e-commerce and social networking, the launching of a new product has to undergo with deep study of customers views on existing products and their requirements in the product. Since a huge amount of reviews are being generated from various source, thereby it is becoming exceedingly difficult to make sense of the data. This project considers the problem of analyzing reviews by their overall semantic that is, positive, negative and neutral behavior. In this work a Webapp is developed that classifies the review to any of the 3 cases. The work here is analyzing and classifying the Product Reviews using Deep Learning.","PeriodicalId":262409,"journal":{"name":"2022 First International Conference on Artificial Intelligence Trends and Pattern Recognition (ICAITPR)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133966310","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 light weight models that run on edge devices for detecting anomalies and events in oil and gas extraction using unsupervised learning and similarity methods","authors":"Srisuhasini Gottumukkala, Amitabha Bhattacharyya","doi":"10.1109/ICAITPR51569.2022.9844225","DOIUrl":"https://doi.org/10.1109/ICAITPR51569.2022.9844225","url":null,"abstract":"Oil extraction is an energy intensive process, if any fault happens it may lead to heavy losses. Electrical Submersible Pump (ESP) is the main equipment used in oil extraction process. The objective of this paper is to describe various methods and procedures for detecting the events or anomalous conditions that occur in the ESP equipment during the oil extraction. The proposed models must work on edge devices to reduce the latency time in detecting the events. The ESP equipment generates tera bytes of data every day and manual surveillance of the data is very difficult or almost impossible. ESP equipment has various sensors which measure different data like discharge pressure (DP), intake pressure (IP), temperature (T), current supplied(I) and vibration(V) etc. Each individual sensor measurement is termed as a signal. There are few methods available for event detection in ESP which uses encoders or pattern recognition models[1]. But these models are not compatible to run on edge devices as they require high computation power. The proposed methodology uses unsupervised learning and similarity methods to detect the anomalies. Simple mathematical or statistical techniques are used in building light weight edge device compatible models. Reliability and completeness of the data is important, and the quality engine identifies the data portions with bad quality, so that these portions can be removed prior to the anomaly detection. Any unusual pattern in more than one signal is considered as anomaly. Event is a known anomaly pattern, for example if discharge pressure decreases and vibration increases these are the symptoms for a solid production event happening. The similarity algorithm used in classifying anomalies into events provide the confidence score for the event swith respect to every type of event and the event type with highest score is assigned as the class label. The proposed framework has multiple models, and the size of the models are in KB’s so that the overall application can run on devices that has RAM available in MB’s and processor with a single core.","PeriodicalId":262409,"journal":{"name":"2022 First International Conference on Artificial Intelligence Trends and Pattern Recognition (ICAITPR)","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120951938","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":"University Admission Prediction Using Google Vertex AI","authors":"J. Katti, Jony Agarwal, Swapnil Bharata, S. Shinde, Saral Mane, Vinod Biradar","doi":"10.1109/ICAITPR51569.2022.9844176","DOIUrl":"https://doi.org/10.1109/ICAITPR51569.2022.9844176","url":null,"abstract":"For a pursuing graduate student, shortlisting the colleges could be an intense issue. College undergraduates frequently have an inclination to ponder over the chance that their profile suits the college requirements. Computer programs are exceptionally well trained and faster than humans in making decisions. Moreover, the cost of admission in a college is a lot, making it very crucial for a student that their profile gets shortlisted for a university admission. A University prediction machine learning algorithm is very advantageous for college undergraduates to choose their dream university which also matches their resume. The proposed method considers diverse variables related to the student and his score in various tests. The dataset includes LOR, GRE score, CGPA, TOEFL score, University rating, SOP, etc. Based on all these criterias, the admission to a particular university of an undergraduate will be predicted.","PeriodicalId":262409,"journal":{"name":"2022 First International Conference on Artificial Intelligence Trends and Pattern Recognition (ICAITPR)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114243080","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}