2021 IEEE Pune Section International Conference (PuneCon)最新文献

{"title":"A Study on Holistic Education for Project Management Using Emotional Intelligence","authors":"R. Bhatnagar, Suman De","doi":"10.1109/punecon52575.2021.9686542","DOIUrl":"https://doi.org/10.1109/punecon52575.2021.9686542","url":null,"abstract":"Emotional Intelligence is an integral part of our life and when it comes to project management it is even more crucial to practice. As project managers we always want to bring the best out of the people we deal with. The best thing about emotional intelligence is that we can develop this skill. We can leverage emotional intelligence to bring such an environment to a workplace where people are being treated as people and not just work resources. By practicing emotional intelligence, a project manager can make sure that the team delivers their best work, they have an environment filled with trust and, they have an open, transparent, supportive work culture. Often, we feel getting carried away with our instant reactions to issues and taking up wrong decisions which we might regret later. This paper talks about our brain circuitry to figure out why we have those common reactions and how we can practice self-regulation and self-mastery.","PeriodicalId":154406,"journal":{"name":"2021 IEEE Pune Section International Conference (PuneCon)","volume":"39 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127713872","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":"CFD Investigation in CD Nozzle at Different Convergence Angles and Constant Divergence Angle and Throat Diameter","authors":"Rushikesh Kore, Shreya Patil, Valentina Victor, S. Suresh, D. Bajaj","doi":"10.1109/punecon52575.2021.9686491","DOIUrl":"https://doi.org/10.1109/punecon52575.2021.9686491","url":null,"abstract":"In aircraft, mechanical, and other engineering applications, nozzles are the most widely utilized equipment. The nozzle is a device that allows the hot exhaust gases produced in the combustion chamber to be accelerated. Nozzle accelerates the flow to supersonic regimes to produce required thrust. This work presents computational approach made to investigate the flow behavior inside the CD nozzle by varying the convergence angle. The characteristics of converging half-angles on different performance parameters are quantitatively studied. In present work convergence angles ranging from 40,45,50 and 55 degrees is being used for investigation. To model the compressible flow of gas within the nozzle as well as its hot exhaust plumes, the k - epsilon analytical equation is used. Exhaust nozzle characteristics were computed and compared to existing empirical evidence to demonstrate the models' correctness. The nozzle model was created with SolidWorks software version (2013), and study will employ Ansys FLUENT software (18.1) to depict fluctuations in velocity, Mach number, pressure, and temperature contours, and the validated CFD process will be used to conduct the CFD investigation.","PeriodicalId":154406,"journal":{"name":"2021 IEEE Pune Section International Conference (PuneCon)","volume":"49 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115323209","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":"Mining Heterogeneous Information Networks: A Review","authors":"Rohit Chivukula, T. Lakshmi","doi":"10.1109/punecon52575.2021.9686506","DOIUrl":"https://doi.org/10.1109/punecon52575.2021.9686506","url":null,"abstract":"An information network is modelled as a graph with vertices denoting entities and links depicting connections within them. Heterogeneous Information Network (HIN) contains multiple types of vertices and multiple types of links. There is vast amount of hidden knowledge available in the HINs. Most of the techniques proposed in the literature are focused on homogeneous networks. The same methods are applied for heterogeneous networks by considering homogeneous projections. But this approach leads to information loss. In this paper, major mining tasks applicable for Heterogeneous Information Networks are reviewed.","PeriodicalId":154406,"journal":{"name":"2021 IEEE Pune Section International Conference (PuneCon)","volume":"51 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114842456","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":"Finding A Baseline Machine Learning Model in Sci-Kit Learn Package in Terms of Accuracy and Efficiency","authors":"S. Bhattacharya, Sayan Kundu, Bipasha Mukhopadhyay, Sinchan Bhattacharya","doi":"10.1109/punecon52575.2021.9686536","DOIUrl":"https://doi.org/10.1109/punecon52575.2021.9686536","url":null,"abstract":"In this research work we have established a baseline machine learning model using the Sci-Kit learn package, that can be used for classification, and would result into optimum accuracy and efficiency, i.e., prediction time. From the time when different models were found in machine learning, the major question was, which is the best suited model. In the modern times, with rise of demand of this field and with introduction of more and more complex datasets, this question remains an important one. The models which we have taken into consideration in this research for comparison are all in terms of classification. The datasets on which the models have been implemented belong to different fields, namely, banking sector, wine recognition, medical sector, environmental sector and occupancy detection. All of these datasets are chosen in such a way that they have different size of attributes, patterns and classes. We have generalized the baseline model selection by experimenting with various classification models and implementing them over a variety of datasets. This research work can be upscaled by considering more models and comparing with the existing ones or taking more datasets for implementation or by doing both.","PeriodicalId":154406,"journal":{"name":"2021 IEEE Pune Section International Conference (PuneCon)","volume":"151 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115176653","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":"Investigation of Weight Initialization Using Fibonacci Sequence on the Performance of Neural Networks*","authors":"D. S. Mukherjee, N. Yeri","doi":"10.1109/punecon52575.2021.9686532","DOIUrl":"https://doi.org/10.1109/punecon52575.2021.9686532","url":null,"abstract":"Initializing weights are important for fast convergence and performance improvement of Artificial Neural Network models. This study proposes a heuristic method to initialize weights for Neural Network with Fibonacci sequence. Experiments have been carried out with different network structures and datasets and results have been compared with other initialization techniques such as Zero, Random, Xavier and He. It has been observed that for small sized datasets, Fibonacci initialization technique reports 94% of test accuracy which is better than Random (85%) and close to Xavier (93%) and He (96%) initialization methods. Also, for medium sized dataset, we have noted that performance of Fibonacci weight initialization method is comparable with the same for Random, Xavier and He initialization techniques.","PeriodicalId":154406,"journal":{"name":"2021 IEEE Pune Section International Conference (PuneCon)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128411497","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 Deep Learning Technique for Emotion Recognition Using Face and Voice Features","authors":"Sukhpreet Kaur, Nilima Kulkarni","doi":"10.1109/punecon52575.2021.9686510","DOIUrl":"https://doi.org/10.1109/punecon52575.2021.9686510","url":null,"abstract":"Automatic emotion recognition is an emerging application in the field of artificial intelligence. Where the use of technology helps to curb various mental illnesses like anxiety, depression, schizophrenia etc. So, there is a need to create efficient artificial intelligent devices. In this experimental project, we developed a multimodal system using neural networks (CNN) for recognizing emotions from facial expressions and voice. We used an RGB images dataset for facial expression recognition. For voice emotion recognition, an audio recorded files dataset was used. We presented phases of automatic emotion recognition in the form of data acquisition, data analysis and data visualization. Comparative analysis among recent papers, features affecting the performance and proposed model in terms of accuracy have also been given in tabular form. The proposed model shows accuracy of 73% and 90.91% for face and voice features respectively. It's observed that variations in the factors of the feature-training phase of neural networks like epochs, batch sizes, training datasets, also affect the results.","PeriodicalId":154406,"journal":{"name":"2021 IEEE Pune Section International Conference (PuneCon)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126455806","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":"Examination of Fake Reviews of Product and Approach to Filter them from Legitimate Reviews","authors":"Devavrat Agnihotri, Saad Ahmed, Dhanashree Darekar, Chinmay Gadkari","doi":"10.1109/punecon52575.2021.9686477","DOIUrl":"https://doi.org/10.1109/punecon52575.2021.9686477","url":null,"abstract":"Product review branding and marketing is important for online retailers. They aid in the development of trust and loyalty, as well as establishing the distinction between your goods and those of competitors. Fake reviews pose a significant challenge to websites and product search engines because they may disrupt customer interest. Although fabricated assessments benefit everybody, the emergence of this dubious strategy is quite intriguing in the long run. The fact that enormous amounts of time, energy, and money are being put into fake review spamming demonstrates how beneficial a decent number of reviews can be. In this manuscript, a conventional method is proposed for the elimination of Fake Reviews on ecommerce sites. The solution is to use the reviewers’ behavior features with review parameters such as the username, IP address and duplicate reviews to mark fake users.","PeriodicalId":154406,"journal":{"name":"2021 IEEE Pune Section International Conference (PuneCon)","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126876837","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 of S-Band Source-Controlled MMIC Voltage Variable Attenuator","authors":"Subham Banerjee, B. Pradhan","doi":"10.1109/PuneCon52575.2021.9686547","DOIUrl":"https://doi.org/10.1109/PuneCon52575.2021.9686547","url":null,"abstract":"The design and simulation of S-Band (2-4 GHz) Voltage Variable Attenuator (VVA) using pseudomorphic High Electron Mobility Transistor (pHEMT) in AWR design environment 13 is presented in this paper. This attenuator can be used in Automatic Gain Control circuits and in calibration purposes. At frequency of 2 GHz, minimum attenuation (at control voltage of 3.95 V) is 2.71195 whereas maximum attenuation (at control voltage of −4 V) is 23.248. S11 and S22 are better than −7 dB. At all control voltage values except at minimum attenuation, the noise figure is less than and equal to the attenuation value. The operating principle of the circuit is also explained in the paper.","PeriodicalId":154406,"journal":{"name":"2021 IEEE Pune Section International Conference (PuneCon)","volume":"115 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114562320","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 Transfer Learning Approach for Descriptive Question Answering System","authors":"Gourishankar Bansode, D. Jha, Atharva Hasabnis, Abinash Nayak, R. Pagare","doi":"10.1109/punecon52575.2021.9686521","DOIUrl":"https://doi.org/10.1109/punecon52575.2021.9686521","url":null,"abstract":"In this era of data explosion, where data is streaming at an exponential rate, efficient strategies of data processing have become an important aspect. The paper focuses on study of current “tate-of-the-art models” and proposes a Transfer learning approach with BERT model fine-tuned on SQuAD v2.0 dataset and improving the overall results based on speed and scaling factors and extending the reach of Question answering systems from generating one-line answers to generate descriptive answers. It is designed to handle user queries, whether it is web-based queries, reading comprehension tests, or Product related enquiries for satisfying user needs. The proposed model was experimented on a custom-made dataset to compare results with the original BERT model and a human-based evaluation method is proposed to evaluate the correctness of the descriptive answers.","PeriodicalId":154406,"journal":{"name":"2021 IEEE Pune Section International Conference (PuneCon)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133429892","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":"Computational Analysis of Flow Field Over Missile Separated from Weapon Bay Cavity at Mach 2 and 5","authors":"Payal Tembhurnikar, Mrunal Bhosale, Pramila Bote, Shreya Jadhav, Vijaykumar Gorfad, D. Sahoo","doi":"10.1109/punecon52575.2021.9686526","DOIUrl":"https://doi.org/10.1109/punecon52575.2021.9686526","url":null,"abstract":"A parametric analysis was conducted to determine the flow over a missile released from the weapon bay cavity passing at a supersonic speed of Mach 2 in comparison with Mach 5. A weapon bay cavity with specified dimensions and a missile at 2.75m distance from bottom cavity wall was tested in compressible flow RANS solver. Detailed information of complicated aerodynamic characteristics like pressure variation, density variation and Mach number was obtained through CFD simulations to study the variation in flow physics over missile. Pressure fluctuation experienced by missile surface is plotted as coefficient of pressure (Cp) data over a missile kept in supersonic flow of Mach 2 and Mach 5. The flow is compared on the basis of flow interaction between shear layer at anterior edge of cavity and the leading-edge shock generated at nose of the missile body. As flow speed is decreased from Mach 5 to Mach 2, this flow interaction has minimal impact. In this paper, two-dimensional CFD simulations in ANSYS FLUENT are carried out on the missile body at an angle of attack of 0 degree 9and Mach number 2.00 and 5.00 with density-based solver, assuming the ideal gas conditions with k-ℰ turbulence model. The study indicates that with decrease in flow Mach number, the flow characteristics changes between cavity and upper surface of missile. The plot of pressure coefficient distribution over missile surface shows significant variation in flow between cavity and upper missile surface with change in freestream Mach number. Configuration moving at supersonic speed of Mach 2 has less concern with the flow interaction and is rather affected by the detached bow shock wave with higher flow turn angle. Due to the compressible behaviour of the flow, a Prandtl-Meyer expansion fan is observed at shoulder of missile nose tip and also at rear end of missile. The effect of flow interaction between the shear layer at front edge of cavity and system of shock wave is major contributor for change in aerodynamic characteristics for model moving at speed of Mach 5. While for Mach 2, strong detached bow shock wave at leading edge of missile is the primary reason.","PeriodicalId":154406,"journal":{"name":"2021 IEEE Pune Section International Conference (PuneCon)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133787685","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}