2021 IEEE International Conference on Electronics, Computing and Communication Technologies (CONECCT)最新文献

{"title":"Question Answering Chatbot using Deep Learning with NLP","authors":"Devanshi Singh, K.Rebecca Suraksha, S. Nirmala","doi":"10.1109/CONECCT52877.2021.9622709","DOIUrl":"https://doi.org/10.1109/CONECCT52877.2021.9622709","url":null,"abstract":"In spite of the number of techniques, models and datasets, Question Answering is still an exacting problem because of the issues in understanding the question and extracting the correct answer. It refers to creating platforms that when given a question in a natural language by humans, can automatically answer it. While many information retrieval chatbots achieve the task, recently, deep learning has earned a lot of attention to question answering due to its capability to learn optimal representation for the given task. This paper aims to build a closed domain, factoid Question Answering system. We recruit NLP methods of pattern matching and information retrieval to create an answer candidate pool. Before scoring similarities between the question and answers, we map them into some feature space. Our approach solves this task through distributional representations of the words and sentences wherein encodings store their lexical, semantic, and syntactic aspects. We use a convolutional neural network architecture to rank these candidate answers. Our model learns an optimal representation for the input question and answer sentences and a matching function to relate each such pair in a supervised manner from training data. Our model does not require any manual feature engineering or language sensitive data; hence can be extended to various domains. Training and testing on TREC QA, a Question Answering dataset, showed very promising metrics for our model.","PeriodicalId":164499,"journal":{"name":"2021 IEEE International Conference on Electronics, Computing and Communication Technologies (CONECCT)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131651417","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 Machine learning based approach for detection of Tumor","authors":"Kirankumar Madihalli, H. Ramya","doi":"10.1109/CONECCT52877.2021.9622571","DOIUrl":"https://doi.org/10.1109/CONECCT52877.2021.9622571","url":null,"abstract":"The tumor is a medical disorder that can be noticed in several parts of the body. A tumor in simple words is the abnormal growth of cells in a particular organ of the body without any control. These cells can interrupt the normal functioning of the brain. It can be found in people of any age, children, teenagers, and adults irrespective of gender. If the tumor is found in the brain, it is referred to as a brain tumor. Brain tumor must be analyzed accurately as it involves the life of a person. The tumor can be of Cancerous Tumor (CT) and Non-cancerous Tumor (NCT) types. The motive of the paper is to develop machine learning algorithms, which can detect the tumor without human interference and classify it as either CT or NCT. Machine learning algorithms developed are logistic regression and fuzzy c means methods. The logistic regression method is developed, it is a statistical model that helps in distinguishing categorical values. The sigmoid function is used to categorize the values. Furthermore, Fuzzy C-Means (FCM) method has also been developed. In the FCM method membership functions are calculated. Finding the similarity of data points is done and forming the clusters. The results of logistic regression and FCM are compared.","PeriodicalId":164499,"journal":{"name":"2021 IEEE International Conference on Electronics, Computing and Communication Technologies (CONECCT)","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126503503","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 Novel Superstrate for Low RCS Antenna","authors":"Vyshnavi S.K. Das, Arti A. Gurap, Hema Singh","doi":"10.1109/CONECCT52877.2021.9622648","DOIUrl":"https://doi.org/10.1109/CONECCT52877.2021.9622648","url":null,"abstract":"Superstrate implementation over the antenna is one of the techniques to reduce the antenna scattering. A novel design of superstrate consisting of periodic structure with varactor diode is presented to demonstrate the RCS reduction of patch antenna array. Radiation and scattering performance of two configurations of superstrate, viz. 2-layered and 3-layered are shown for both single patch and 4-element patch array. In each case, it is shown that significant RCSR is achieved over X-band without degrading VSWR and the antenna gain.","PeriodicalId":164499,"journal":{"name":"2021 IEEE International Conference on Electronics, Computing and Communication Technologies (CONECCT)","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126524825","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 High Field effect Mobility in Carbon Nanotube FETs(CNTFETs)","authors":"Satyam Singh, Basavprasad Siriyannavar, Sidharth Sitesh, P. Vimala, T. Arunsamuel","doi":"10.1109/CONECCT52877.2021.9622595","DOIUrl":"https://doi.org/10.1109/CONECCT52877.2021.9622595","url":null,"abstract":"This paper analyzed the Carbon Nano Tube (CNT) field-effect carrier mobility at the low field in the back-gated CNT-FET devices. This model is based on calculating the mean free paths of carrier concerning the several scattering mechanisms and multi-band transport. The mobility-based parameters like charge density and conductance are analyzed by varying Carbon Nano Tube”s length and diameter. It's observed that high ballistic transport was achieved when the length of CNT was less than the mean free path of carrier.","PeriodicalId":164499,"journal":{"name":"2021 IEEE International Conference on Electronics, Computing and Communication Technologies (CONECCT)","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114193895","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, Modeling and Simulation of Micromechanical Suspension System for the Detection of Screech","authors":"A. Sthuthi, C.S Bhoomika","doi":"10.1109/CONECCT52877.2021.9622570","DOIUrl":"https://doi.org/10.1109/CONECCT52877.2021.9622570","url":null,"abstract":"High performance military gas turbine engines are often equipped with augmenters to provide increased level of thrust for relatively short period of time. The augmentation level which can be supplied by engines, is limited by the combustion instabilities, screech and rumble. Screech is a loud, high pitched sound that can cause rapid failure of the mechanical components and also be a threat in combat situations when the military flights can be detected by the enemy due to the intense sound. For the avoidance of these consequences due to instabilities, a MEMS accelerometer herein is proposed and addressed that can detect screech frequencies. The current work deals with design and comparison of two different mechanical suspension systems of a single axis MEMS accelerometer, namely parallel beam and folded beam for its improved sensitivity based on SOI MUMPs fabrication process flow by MEMSCAP foundry. Correspondingly, the analytical modeling for designing the suspension system and combs is presented. Initially, a system level analytical modeling is done, followed by a device level design by building geometrical models using FE simulator COMSOL Multiphysics and MATLAB and a comparative analysis is carried out. Various design parameters like resonant frequency, mechanical and electrical sensitivity, static capacitance, cross axis sensitivity and Bandwidth Vs Sensitivity analysis are also attained and compared. The sensitivity of the parallel beam is found to be 9.925nm/g and folded beam is 17.1nm/g hence inferred that folded beam gives 1.7 times improved sensitivity and the mechanical stress detected by the folded beam is less than parallel beam suspension thus reflecting the better performance of a folded beam suspension. The novelty of the design lies in the fact that the device gives a stable performance over 1g to 1000g of acceleration due to gravity (g = 10 m/s2) and also provides fine sensitivity.","PeriodicalId":164499,"journal":{"name":"2021 IEEE International Conference on Electronics, Computing and Communication Technologies (CONECCT)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122862879","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 Pilot Study on Wearable Nasal Patch Sensor for Assessment of Breathing Parameters","authors":"Rishaab Pavan, N. Sriraam, BR Purnima, D. Rakshith, Nupur Ravindran, NG Prajwala, Gayathri HJ Devi","doi":"10.1109/CONECCT52877.2021.9622650","DOIUrl":"https://doi.org/10.1109/CONECCT52877.2021.9622650","url":null,"abstract":"The use of variable sensors for the monitoring of respiratory parameters has gained popularity over the recent years. Patch based electronic sensors are newly emerged state of the art sensing methods in which the user is directly augmented with technology. Advances in patch electronic sensors along with broad availability of smartphones, cloud and wireless systems has empowered wearable technology for a huge impact on digital and personal health care. This pilot study proposes a context recognition method using sensor data obtained from one and both nostrils simultaneously. An electronic nasal patch- based sensor module is developed to asses breathing patterns. The first level prototype developed using NTC thermistor was found to be compact and efficient towards recording inhalation and exhalation rates, respiration rate and different breath parameters such as volume and max flow rate. The raw data obtained from this module was processed for removal of base line drift and noise using a mean smoothed windowed. Therefore, the low thermistor driven patch sensing mechanism helped in measuring inhalation and exhalation processes effectively. In this pilot study we have obtained the mean, median and standard deviation values for different breathing parameters. The statistical parameters indicate the presence of variation between inhalation and exhalation breathing patterns.","PeriodicalId":164499,"journal":{"name":"2021 IEEE International Conference on Electronics, Computing and Communication Technologies (CONECCT)","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127827980","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":"Paper Title","authors":"T. Schwarz","doi":"10.1109/conecct52877.2021.9622649","DOIUrl":"https://doi.org/10.1109/conecct52877.2021.9622649","url":null,"abstract":"This paper presents the implementation of the overlapping grid technique into DLR’s structured flow solver FLOWer. The hole cutting procedure and the search methods are described. Trilinear interpolation is used to transfer flow data between grids. For data interpolation close to solid surfaces, a projection algorithm is applied which corrects discretization effects. The approach used to prescribe rigid body motions for unsteady flow simulations allows to relate the motion of any body to any other body. Unsteady simulations also require to consider the hole motion during the definition of the interpolation points. For the integration of forces on grids with mesh overlap on body surfaces a unique surface is generated. Background grids are created with a Cartesian grid generator, which allows for cubic and anisotropic cells. Several examples of applications demonstrate the generality of the implementation of the Chimera technique.","PeriodicalId":164499,"journal":{"name":"2021 IEEE International Conference on Electronics, Computing and Communication Technologies (CONECCT)","volume":"72 8","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134427178","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":"Identity Verification Using Age Progression & Machine Learning","authors":"Shweta Taneja, Sanchit Gupta, Ashwani Jaiswal, Dhruva Bansal, A. Bansal","doi":"10.1109/CONECCT52877.2021.9622683","DOIUrl":"https://doi.org/10.1109/CONECCT52877.2021.9622683","url":null,"abstract":"Facial age progression is the process of synthesizing a face image at an older age based on images showing a person at a younger age. The ability to generate accurate age progressed face images is important for a number of forensic investigation tasks. In this paper we analyze the performance of a number of publicly available age progression applications, with respect to different parameters encountered in age progression including imaging conditions of input images, presence of occluding structures, age of input/target faces, and age progression range. Through the examination and measurement of old enough movement precision within the sight of various conditions, we remove various ends that appear as a bunch of rules identified with factors that criminological craftsmen and age movement scientists should concentrate to deliver improved age movement techniques. Trial results utilizing an information base consisting of sets of face pictures that were recovered from the FGNET dataset. The check framework for faces isolated by as many AI calculations, accomplishes an equivalent exactness pace of 80%.","PeriodicalId":164499,"journal":{"name":"2021 IEEE International Conference on Electronics, Computing and Communication Technologies (CONECCT)","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115038337","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 sequencing circuit to provide power up/down sequence to multiple outputs of a dc-dc converter for space application","authors":"A. Anand, Shreeti Goyal, Shivaprakash B, K. Gupta","doi":"10.1109/CONECCT52877.2021.9622546","DOIUrl":"https://doi.org/10.1109/CONECCT52877.2021.9622546","url":null,"abstract":"In multi-rail complex power systems of loads like ASICs, FPGAs, DSPs, GaAs FET based Solid State Power Amplifier (SSPA), very specific power up and power down sequencing of different rail supplies is required, in order to guarantee reliable operation of these devices. For example, GaAs FET based SSPA has a special requirement that at Turn ON, output voltages should appear in a sequence of first −5V, then +8V followed by +15V. During turn OFF, +8V first, then +15V and last −5V should go low. This special requirement is because the GaAs FET used in SSPA is depletion type FET which requires a negative Gate bias (−5V) first and then Drain supply (+8V). Drain supply without proper gate bias may result in excessive drain current leading to the failure of GaAs FET. +15V O/P which supplies power to RF generator circuit, appearing after +8V will ensure input signal to amplifier after establishing the supply. Making an independent ‘Output Sequencing circuit’ proposed in this paper, offers advantages as follows: (a) It can be planned as a part of user package and can be used with any DC-DC converter which meets the load current/voltage requirements. (b) If there is a short circuit at DC-DC converter O/P, the converter will enter its own current limit protection. If the short circuit/ overload is at Load end on +15V or +8V line, DC-DC will enter its own current limit protection. Overload or short circuit on −5V O/P (>85mA) will result in turn OFF of all the O/Ps. Hence the sequence of outputs during turn ON & turn OFF is guaranteed (c) +15V O/P will never appear earlier than +8V O/P. (d) +8V O/P has internal low drop out regulator (LDO) to give very tight regulation for load range of 0.2A to 2A. No overshoot/ undershoot during load transient of +8V, hence this circuit supports large load transients on +8V output. The hardware circuit was realized & has successfully completed all the tests. This circuit has been realized in HMC form to reduce size and ease of accommodation in user packages.","PeriodicalId":164499,"journal":{"name":"2021 IEEE International Conference on Electronics, Computing and Communication Technologies (CONECCT)","volume":"295 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115403183","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":"Speech Emotional Recognition Using CNN Algorithm","authors":"N. M, P. N, Priyanka, Palaniappan Sambandam","doi":"10.1109/CONECCT52877.2021.9622714","DOIUrl":"https://doi.org/10.1109/CONECCT52877.2021.9622714","url":null,"abstract":"Discourse Emotional Recognition is a method of analyzing the expressions of the human and determining the actual emotion of user through tone analysis and text analysis. Text analysis uses SVM algorithm and tone analysis uses CNN algorithm. Emotion expressed through words differs from emotion expressed through the speaker's tone. This paper focuses on determining the speaker's exact emotions by analyzing both the words and the tone of talk. At the point when the two practices are utilized together, compelling outcomes are acquired. This was intended to help the association in understanding the perspective of the customer on the item dependent on the feeling acknowledgment.","PeriodicalId":164499,"journal":{"name":"2021 IEEE International Conference on Electronics, Computing and Communication Technologies (CONECCT)","volume":"189 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123200979","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}