Conference Papers
Permanent URI for this collectionhttps://idr.nitk.ac.in/handle/123456789/28506
Browse
6 results
Search Results
Item Currency recognition system using image processing(Institute of Electrical and Electronics Engineers Inc., 2017) Abburu, V.; Gupta, S.; Rimitha, S.R.; Mulimani, M.; Koolagudi, S.G.In this paper, we propose a system for automated currency recognition using image processing techniques. The proposed method can be used for recognizing both the country or origin as well as the denomination or value of a given banknote. Only paper currencies have been considered. This method works by first identifying the country of origin using certain predefined areas of interest, and then extracting the denomination value using characteristics such as size, color, or text on the note, depending on how much the notes within the same country differ. We have considered 20 of the most traded currencies, as well as their denominations. Our system is able to accurately and quickly identify test notes. © 2017 IEEE.Item Measuring the influence of moods on stock market using Twitter analysis(Springer Verlag service@springer.de, 2019) Cowlessur, S.K.; Annappa, B.; Sree, B.K.; Gupta, S.; Velaga, C.It is a well-known fact that sentiments play a vital role and is an incredibly influential tool in several aspects of human life. Sentiments also drive proactive business solutions. Studies have shown that the more appropriate data is gathered and analyzed at the right time, the higher the success of sentiment analysis. This paper analyses the correlation between the public mood and the variation in stock prices towards companies in different domains. For each tweet, scores are assigned to eight predefined moods namely “Joy†, “Sadness†, “Fear†, “Anger†, “Trust†, “Disgust†, “Surprise†and “Anticipation†. A regression model is applied to the mood scores and the stock prices dataset to obtain the R-squared score, which is a metric used to evaluate the model. The paper aims to find the moods that best reflect the stock values of the respective companies. From the results, it is observed that there is a definite correlation between public mood and stock market. © Springer Nature Singapore Pte Ltd. 2019.Item Design and evaluation of COBALT queue discipline(IEEE Computer Society help@computer.org, 2019) Palmei, J.; Gupta, S.; Imputato, P.; Morton, J.; Tahiliani, M.P.; Avallone, S.; Täht, D.The problem of bufferbloat arises due to the presence of large unmanaged buffers and leads to high queuing delays and significant degradation in the performance of time-sensitive and interactive Internet applications. Recently, a new smart queue management system called Common Applications Kept Enhanced (CAKE) has been introduced in Linux 4.19 to tackle the problem of bufferbloat in home Internet gateways. One of the integral parts of CAKE system is COBALT (CoDel and BLUE Alternate), a queue discipline which is a combination of Controlled Delay (CoDel) and BLUE algorithms. Although CAKE is a part of the Linux kernel, a detailed discussion on the design of COBALT is missing. In this paper, we discuss the design of COBALT and compare its performance with CoDel. Additionally, we propose a simulation model for COBALT in ns-3 and test its correctness by comparing the results obtained from it to those obtained from the Linux model. Our evaluation shows that COBALT offers substantial benefits in terms of curtailing queue delays when unresponsive flows exist. © 2019 IEEE.Item Quantum Machine Learning: A Review and Current Status(Springer Science and Business Media Deutschland GmbH, 2021) Mishra, N.; Kapil, M.; Rakesh, H.; Anand, A.; Mishra, N.; Warke, A.; Sarkar, S.; Dutta, S.; Gupta, S.; Prasad Dash, A.; Gharat, R.; Chatterjee, Y.; Roy, S.; Raj, S.; Kumar Jain, V.; Bagaria, S.; Chaudhary, S.; Singh, V.; Maji, R.; Dalei, P.; Behera, B.K.; Mukhopadhyay, S.; Panigrahi, P.K.Quantum machine learning is at the intersection of two of the most sought after research areas—quantum computing and classical machine learning. Quantum machine learning investigates how results from the quantum world can be used to solve problems from machine learning. The amount of data needed to reliably train a classical computation model is evergrowing and reaching the limits which normal computing devices can handle. In such a scenario, quantum computation can aid in continuing training with huge data. Quantum machine learning looks to devise learning algorithms faster than their classical counterparts. Classical machine learning is about trying to find patterns in data and using those patterns to predict further events. Quantum systems, on the other hand, produce atypical patterns which are not producible by classical systems, thereby postulating that quantum computers may overtake classical computers on machine learning tasks. Here, we review the previous literature on quantum machine learning and provide the current status of it. © 2021, Springer Nature Singapore Pte Ltd.Item A Shadow Based Low-Cost Hand Movement Recognition System for Human Computer Interaction(Institute of Electrical and Electronics Engineers Inc., 2021) Geetha, V.; Salvi, S.; Sahoo, P.; Dodiya, M.; Gupta, S.TIn this paper, we propose and implement a real-time hand motion detection system which uses shadows projected by hand and detected by low cost Light Dependent Resistor (LDR). The main advantage of the shadow approach is real-time recognition and its application in Post COVID 19 world where contactless interactions are required. Our proposed approach uses 2D hand motion shadows to determine sequence of light blocking the LDRs and thus making the system less complex and less compute intensive compared to 3D image recognition based systems. The accuracy of the proposed system is tested under various lighting conditions and 82-95\% accuracy is observed under normal lighting conditions. © 2021 IEEE.Item Performance Analysis and Loss Estimation of an AC-DC PFC Topologies of an EV Charger(Institute of Electrical and Electronics Engineers Inc., 2023) Gupta, S.; Vignesh Kumar, V.V.The front-end AC-DC power factor correction (PFC) converter of an electric vehicle (EV) charger is essential to achieve the grid side power factor close to unity and maintain the input current total harmonic distortion (THD) within permissible limits. The other desirable attributes are high power density, high efficiency, and simple structure. However, several articles have discussed the different PFC topologies to achieve these qualities with the difference in the number of switching devices employed and conduction modes. So, this paper aims to present the design and performance comparison of four common PFC topologies. Further, the loss analysis using the datasheet parameters of switching devices and operational modes of the PFC converters have been discussed. The converters, namely, active boost PFC, interleaved-boost PFC, dual boost PFC and totem-pole PFC, have been designed for CCM operation with the output power/voltage of 3. 3kW/400V. Moreover, these topologies are simulated in MATLAB/ Simulink, and their performances in terms of the amount of THD in input current, output voltage regulation, and switching losses have been obtained. The analysis shows that the bridgeless totem-pole PFC converter shows superior performance among all four topologies taken for study due to a low number of switching devices in the current conduction path and reduced switching losses. © 2023 IEEE.