Pub Date : 2023-05-25DOI: 10.1109/IConSCEPT57958.2023.10170449
Indra Kumar Chaudhry, Chaudhary Pratap Singh, Ravi Nandan Ray
An energy-efficient and optimized voltage CMOS voltage level shifter is proposed in this paper. There are several uses for the CMOS Voltage level shifters (LS) in power supply architecture. The voltage level shifter’s main function is to change the voltage level from low to high and vice versa. The proposed voltage LS circuit design uses a select signal (Vin) voltage switch logic, which accepts an input signal between 0.3 Volt and 0.6 Volt and produces an output signal with peak-to-peak voltage ranging from 1.2Volt to 0.6 Volt. The proposed LS circuit design is validated in ASAP7 7nm Fin-Fet technology, it outperforms a recently Wilson current mirror level shifter with Zero threshold voltage architecture in terms of latency and power dissipation by 42.76% and 39.6%, respectively. Power consumption and propagation delay are both significantly minimized by the proposed design topology.
{"title":"A Voltage Level Shifter Design for High Performance Application in Near Threshold Voltage Regime","authors":"Indra Kumar Chaudhry, Chaudhary Pratap Singh, Ravi Nandan Ray","doi":"10.1109/IConSCEPT57958.2023.10170449","DOIUrl":"https://doi.org/10.1109/IConSCEPT57958.2023.10170449","url":null,"abstract":"An energy-efficient and optimized voltage CMOS voltage level shifter is proposed in this paper. There are several uses for the CMOS Voltage level shifters (LS) in power supply architecture. The voltage level shifter’s main function is to change the voltage level from low to high and vice versa. The proposed voltage LS circuit design uses a select signal (Vin) voltage switch logic, which accepts an input signal between 0.3 Volt and 0.6 Volt and produces an output signal with peak-to-peak voltage ranging from 1.2Volt to 0.6 Volt. The proposed LS circuit design is validated in ASAP7 7nm Fin-Fet technology, it outperforms a recently Wilson current mirror level shifter with Zero threshold voltage architecture in terms of latency and power dissipation by 42.76% and 39.6%, respectively. Power consumption and propagation delay are both significantly minimized by the proposed design topology.","PeriodicalId":240167,"journal":{"name":"2023 International Conference on Signal Processing, Computation, Electronics, Power and Telecommunication (IConSCEPT)","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115982990","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}
Pub Date : 2023-05-25DOI: 10.1109/IConSCEPT57958.2023.10170027
Somya Srivastav, Kalpna Guleria, Shagun Sharma
A software that examines network traffic and searches for inconsistencies is known as an Intrusion Detection System (IDS). Network changes that seem to be abnormal or unexpected could be evidence of fraud at any phase, from the beginning of an attempt through the end of an intrusion. Data sharing is required to be safe since it primarily relies on the internet. Encryption processes and verification are unsuitable for internet security, and firewalls are unable to recognize fragmented fake transmissions. Additionally, attackers frequently update their strategy, tools, techniques, and tactics, which can have bad consequences like productivity losses, financial harm, data loss, etc. Therefore, it is essential to set up a trustworthy IDS, which is an extremely difficult task. In this work, the accuracy of an IDS system is forecasted by using a variety of supervised Machine Learning (ML) algorithms, including Decision tree (DT), Random Forest (RT), K-Nearest Neighbor (KNN), and Logistic Regression (LR) models. For the analysis, the dataset is collected from Kaggle, and the method that produces the highest accuracy is recommended for making future forecasts of intrusion. Furthermore, the outcomes have resulted in accuracy, execution speed, precision, F-measure, and recall. Additionally, the random forest performed best with the highest accuracy of 98.65% which can be recommended for the enhanced dataset to be implemented for better results for an IDS.
{"title":"Machine Learning Based Predictive Model for Intrusion Detection","authors":"Somya Srivastav, Kalpna Guleria, Shagun Sharma","doi":"10.1109/IConSCEPT57958.2023.10170027","DOIUrl":"https://doi.org/10.1109/IConSCEPT57958.2023.10170027","url":null,"abstract":"A software that examines network traffic and searches for inconsistencies is known as an Intrusion Detection System (IDS). Network changes that seem to be abnormal or unexpected could be evidence of fraud at any phase, from the beginning of an attempt through the end of an intrusion. Data sharing is required to be safe since it primarily relies on the internet. Encryption processes and verification are unsuitable for internet security, and firewalls are unable to recognize fragmented fake transmissions. Additionally, attackers frequently update their strategy, tools, techniques, and tactics, which can have bad consequences like productivity losses, financial harm, data loss, etc. Therefore, it is essential to set up a trustworthy IDS, which is an extremely difficult task. In this work, the accuracy of an IDS system is forecasted by using a variety of supervised Machine Learning (ML) algorithms, including Decision tree (DT), Random Forest (RT), K-Nearest Neighbor (KNN), and Logistic Regression (LR) models. For the analysis, the dataset is collected from Kaggle, and the method that produces the highest accuracy is recommended for making future forecasts of intrusion. Furthermore, the outcomes have resulted in accuracy, execution speed, precision, F-measure, and recall. Additionally, the random forest performed best with the highest accuracy of 98.65% which can be recommended for the enhanced dataset to be implemented for better results for an IDS.","PeriodicalId":240167,"journal":{"name":"2023 International Conference on Signal Processing, Computation, Electronics, Power and Telecommunication (IConSCEPT)","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114459569","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}
Pub Date : 2023-05-25DOI: 10.1109/IConSCEPT57958.2023.10170303
G. Sreeramulu Mahesh, M. Chandrashekar, A. Muni Sankar, S. Mohan, S. Chandra Sekhar, P. S. Ranjit
Most of the IT industries with microgrids are facing the impacts of harmonics on lighting loads, UPS, Elevators and Air Handling Units with Variable Frequency Drives, thus reduces the equipment performance and its life cycle. Many passive filters like single tuned filter, double tuned filter or combination of both single and double tuned filters et are implemented practically in the industries. It requires a careful tuning, otherwise, the resonance problems will arouse in the entire microgrid and leads to instability between the generation and loads, thus the design of an optimized passive filter is still a challenging problem for mitigating the harmonics. The Cuckoo Search Algorithm (CSA) is proposed in this paper to design the passive harmonic filter to reduce the Total Harmonic Distortion and size of the filter, which provides better tuning than the manual tuning. The advantages of this algorithm are: simple and provides less latency in processing in the iterations. This CSA is implemented on real time data from an IT industry with Fluke analyzer and the filter design is carried out using MATLAB simulation software and desired waveforms are presented.
{"title":"An Optimized Filter Design with Cuckoo Search Algorithm for Industrial Microgrids","authors":"G. Sreeramulu Mahesh, M. Chandrashekar, A. Muni Sankar, S. Mohan, S. Chandra Sekhar, P. S. Ranjit","doi":"10.1109/IConSCEPT57958.2023.10170303","DOIUrl":"https://doi.org/10.1109/IConSCEPT57958.2023.10170303","url":null,"abstract":"Most of the IT industries with microgrids are facing the impacts of harmonics on lighting loads, UPS, Elevators and Air Handling Units with Variable Frequency Drives, thus reduces the equipment performance and its life cycle. Many passive filters like single tuned filter, double tuned filter or combination of both single and double tuned filters et are implemented practically in the industries. It requires a careful tuning, otherwise, the resonance problems will arouse in the entire microgrid and leads to instability between the generation and loads, thus the design of an optimized passive filter is still a challenging problem for mitigating the harmonics. The Cuckoo Search Algorithm (CSA) is proposed in this paper to design the passive harmonic filter to reduce the Total Harmonic Distortion and size of the filter, which provides better tuning than the manual tuning. The advantages of this algorithm are: simple and provides less latency in processing in the iterations. This CSA is implemented on real time data from an IT industry with Fluke analyzer and the filter design is carried out using MATLAB simulation software and desired waveforms are presented.","PeriodicalId":240167,"journal":{"name":"2023 International Conference on Signal Processing, Computation, Electronics, Power and Telecommunication (IConSCEPT)","volume":"140 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114834294","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}
Electric Vehicles are powered by electric motors rather than internal combustion engines, and they use electricity as their primary fuel. A number of energy sources, such as batteries, fuel cells, and solar panels, can be used to power EVs. They are becoming increasingly popular as an alternative to traditional gasoline-powered vehicles because they produce fewer emissions and can be more efficient and cost-effective to operate. In general, electric vehicle technology is advancing and changing and has the potential to lessen our dependency on fossil fuels and contribute to the fight against climate change. So as we need fuel stations for fuel-based vehicles, we need charging stations for electrical vehicles. But as of now, use of the electric vehicles in India is very limited; thus, finding information on these charging stations or their exact location is very hard. One of the best ways to help overcome such situations is to make an application for the electrical vehicle which will display the appropriate information about charging stations and give directions, on the location of the charging stations. EV Sahayak is one such helping application that gives the location of the charging station, helps the user with their payments, manages their files or documents, and gives some information about the parts of the vehicle, and hardware.
{"title":"EV Sahayak: Android Assistance App for Electric Vehicle","authors":"Swati V. Jadhav, Sidhesh Marne, Soham Phadke, Tilak Solunke, Tanmayee Suryawanshi","doi":"10.1109/IConSCEPT57958.2023.10170158","DOIUrl":"https://doi.org/10.1109/IConSCEPT57958.2023.10170158","url":null,"abstract":"Electric Vehicles are powered by electric motors rather than internal combustion engines, and they use electricity as their primary fuel. A number of energy sources, such as batteries, fuel cells, and solar panels, can be used to power EVs. They are becoming increasingly popular as an alternative to traditional gasoline-powered vehicles because they produce fewer emissions and can be more efficient and cost-effective to operate. In general, electric vehicle technology is advancing and changing and has the potential to lessen our dependency on fossil fuels and contribute to the fight against climate change. So as we need fuel stations for fuel-based vehicles, we need charging stations for electrical vehicles. But as of now, use of the electric vehicles in India is very limited; thus, finding information on these charging stations or their exact location is very hard. One of the best ways to help overcome such situations is to make an application for the electrical vehicle which will display the appropriate information about charging stations and give directions, on the location of the charging stations. EV Sahayak is one such helping application that gives the location of the charging station, helps the user with their payments, manages their files or documents, and gives some information about the parts of the vehicle, and hardware.","PeriodicalId":240167,"journal":{"name":"2023 International Conference on Signal Processing, Computation, Electronics, Power and Telecommunication (IConSCEPT)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114571063","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}
Pub Date : 2023-05-25DOI: 10.1109/IConSCEPT57958.2023.10170306
K. R. Chithra, M. Sinith
Time-frequency analysis is an efficient tool for analyzing an audio signal due to its quasi stationary nature. The spectral analysis gives important information about an audio signal such as pitch, onset detection, feature extraction etc. Time-frequency analysis combine both time and frequency domain analysis to provide better understanding of an audio signal. By analyzing a signal in both domains simultaneously, we can track how the frequency content of signal changes over time and how time varying properties impact its spectral characteristics. In this paper a comprehensive study on various methods for time-frequency analysis for musical signals is presented.
{"title":"A Comprehensive Study of Time-Frequency Analysis of Musical Signals","authors":"K. R. Chithra, M. Sinith","doi":"10.1109/IConSCEPT57958.2023.10170306","DOIUrl":"https://doi.org/10.1109/IConSCEPT57958.2023.10170306","url":null,"abstract":"Time-frequency analysis is an efficient tool for analyzing an audio signal due to its quasi stationary nature. The spectral analysis gives important information about an audio signal such as pitch, onset detection, feature extraction etc. Time-frequency analysis combine both time and frequency domain analysis to provide better understanding of an audio signal. By analyzing a signal in both domains simultaneously, we can track how the frequency content of signal changes over time and how time varying properties impact its spectral characteristics. In this paper a comprehensive study on various methods for time-frequency analysis for musical signals is presented.","PeriodicalId":240167,"journal":{"name":"2023 International Conference on Signal Processing, Computation, Electronics, Power and Telecommunication (IConSCEPT)","volume":"55 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129199129","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}
Pub Date : 2023-05-25DOI: 10.1109/IConSCEPT57958.2023.10170235
Roshini Parameswaran, V. P. G. Sivabalan, Shrinithi Rajendran, T. S. Jayaraman
Reconfigurable Intelligent Surface (RIS/IRS) technology has the potential of improving coverage, capacity, and energy efficiency in wireless communication. RIS has control over the scattering and propagation of the transmitted signal to the receiver and it improves the Signal to Noise Ratio (SNR). The new encoding Non-Orthogonal Multiple Access (NOMA) system provide immense connectivity to the users from the base station at low latency. In an ideal scenario, the RIS completely compensate the phase of the signal, but this is not possible in a practical environment. The RIS using discrete phase shifters are analyzed with power variation for the near and far users. The probability error of the RIS-assisted NOMA system is analyzed for the various quantized bits of phase shifter which are one-bit shifter $(0, pi)$, two-bit shifter $(0, pi/2, pi, 3pi/2)$ and three-bit shifter $(0, pi/4,pi/2,3pi/4, pi, 5pi/4,3pi/2,7pi/4)$. The quantized phase shifters at the RIS degrade the Bit Error Rate (BER) performance and are compared with the ideal continuous phase shifter. This research shows that, while using a one-bit phase shifter the presence of residue reduces the system’s performance. Further, increasing the levels of the phase shifter to two-bit and three-bit improves the system performance compared to the one-bit phase shifter.
{"title":"Performance Analysis of RIS Assisted Power Domain NOMA System with Discrete Phase Shifter","authors":"Roshini Parameswaran, V. P. G. Sivabalan, Shrinithi Rajendran, T. S. Jayaraman","doi":"10.1109/IConSCEPT57958.2023.10170235","DOIUrl":"https://doi.org/10.1109/IConSCEPT57958.2023.10170235","url":null,"abstract":"Reconfigurable Intelligent Surface (RIS/IRS) technology has the potential of improving coverage, capacity, and energy efficiency in wireless communication. RIS has control over the scattering and propagation of the transmitted signal to the receiver and it improves the Signal to Noise Ratio (SNR). The new encoding Non-Orthogonal Multiple Access (NOMA) system provide immense connectivity to the users from the base station at low latency. In an ideal scenario, the RIS completely compensate the phase of the signal, but this is not possible in a practical environment. The RIS using discrete phase shifters are analyzed with power variation for the near and far users. The probability error of the RIS-assisted NOMA system is analyzed for the various quantized bits of phase shifter which are one-bit shifter $(0, pi)$, two-bit shifter $(0, pi/2, pi, 3pi/2)$ and three-bit shifter $(0, pi/4,pi/2,3pi/4, pi, 5pi/4,3pi/2,7pi/4)$. The quantized phase shifters at the RIS degrade the Bit Error Rate (BER) performance and are compared with the ideal continuous phase shifter. This research shows that, while using a one-bit phase shifter the presence of residue reduces the system’s performance. Further, increasing the levels of the phase shifter to two-bit and three-bit improves the system performance compared to the one-bit phase shifter.","PeriodicalId":240167,"journal":{"name":"2023 International Conference on Signal Processing, Computation, Electronics, Power and Telecommunication (IConSCEPT)","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114596059","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}
Pub Date : 2023-05-25DOI: 10.1109/IConSCEPT57958.2023.10170001
S. Nithya, T. Sridarshini
In recent year, every optical computing system and optical communication system depends on the photonic crystal. Based on their design, techniques and application the six all optical logic gates such as AND, OR, NOT, XOR, NOR and NAND are analyzed with contrast ratio and response time. Comparison is done based on types of defects, preferred structures for designing the logic gates. Gates designed with T, Y, E etc. where analysed and are reported. Most commonly they form a suitable candidature for high speed optical systems.
{"title":"A Review on 2D Photonic Crystal based All Optical Logic Gates","authors":"S. Nithya, T. Sridarshini","doi":"10.1109/IConSCEPT57958.2023.10170001","DOIUrl":"https://doi.org/10.1109/IConSCEPT57958.2023.10170001","url":null,"abstract":"In recent year, every optical computing system and optical communication system depends on the photonic crystal. Based on their design, techniques and application the six all optical logic gates such as AND, OR, NOT, XOR, NOR and NAND are analyzed with contrast ratio and response time. Comparison is done based on types of defects, preferred structures for designing the logic gates. Gates designed with T, Y, E etc. where analysed and are reported. Most commonly they form a suitable candidature for high speed optical systems.","PeriodicalId":240167,"journal":{"name":"2023 International Conference on Signal Processing, Computation, Electronics, Power and Telecommunication (IConSCEPT)","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126740969","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}
Pub Date : 2023-05-25DOI: 10.1109/IConSCEPT57958.2023.10170387
S. E. F. Sherley, K. Harshitha, R.Siva Subetha, T. Thanigaivasan, R. Prabakaran, S. Lakshmi
Change detection involves quantifying temporal effects with a multi-temporal dataset. Remote sensing data have been extensively utilised for change detection in recent decades. Unsupervised learning is used to analyse satellite imagery or remote sensing data to find changes in land cover or land use over time without the use of labelled training data. Unsupervised learning is a type of machine learning that identifies patterns in data without the use of labels or prior knowledge. The general goal of change detection in remote sensing is to recognise the type of changes in specific geographic locations, and then quantify and assess changes in the regions. In this work, land change detection is analysed using various deep clustering techniques with multitemporal satellite images from different geographical locations. Two models, namely a deep-embedded clustering model, a sparse auto-encoding model are built and trained using both K-Means Clustering and FuzzyC-Means Clustering algorithms in clustering layer. The implemented models address the issue of mixed pixel clustering by using Fuzzy-C Means Clustering to determine whether region has changed over time using satellite images. The implementation is carried out in constrained environment with limited dataset and computational facilities. Deep clustering approaches necessitate high-quality data in order to produce accurate results. Poor-quality data can result in inaccurate clustering results, which can have an impact on the interpretation and application of the results. Due to cloud cover, atmospheric interference, and sensor limitations, environmental data can frequently have issues with noise, missing values, and data gaps, which can impair the quality of the clustering results and in turn, it misleads generation of changed regions. These constraints can have an impact on the quality of the data and make deep clustering approaches difficult to implement. The results of the implemented work have been assessed using Mean Square Error which is a function used to calculate the loss of a model and the effectiveness of a clustering technique is assessed by the silhouette score.
变化检测涉及使用多时间数据集量化时间效应。近几十年来，遥感数据已广泛用于变化探测。无监督学习用于分析卫星图像或遥感数据，以发现土地覆盖或土地利用随时间的变化，而不使用标记训练数据。无监督学习是一种机器学习，它在不使用标签或先验知识的情况下识别数据中的模式。遥感变化检测的总体目标是识别特定地理位置的变化类型，然后量化和评估该区域的变化。在这项工作中，利用不同地理位置的多时相卫星图像，使用各种深度聚类技术分析了土地变化检测。在聚类层分别使用K-Means聚类算法和FuzzyC-Means聚类算法建立并训练了深度嵌入聚类模型和稀疏自编码模型。实现的模型通过使用Fuzzy-C Means clustering来确定区域是否随着卫星图像的时间变化，从而解决了混合像素聚类的问题。该算法是在数据集和计算设备有限的约束环境下实现的。为了产生准确的结果，深度聚类方法需要高质量的数据。质量差的数据可能导致不准确的聚类结果，这可能对结果的解释和应用产生影响。由于云层覆盖、大气干扰和传感器的限制，环境数据经常会出现噪声、缺失值和数据缺口等问题，这些问题会损害聚类结果的质量，反过来，它会误导生成变化区域。这些约束可能对数据质量产生影响，并使深度聚类方法难以实现。使用均方误差(用于计算模型损失的函数)评估了实施工作的结果，并通过剪影分数评估了聚类技术的有效性。
{"title":"Unsupervised change detection analysis using deep clustering frameworks","authors":"S. E. F. Sherley, K. Harshitha, R.Siva Subetha, T. Thanigaivasan, R. Prabakaran, S. Lakshmi","doi":"10.1109/IConSCEPT57958.2023.10170387","DOIUrl":"https://doi.org/10.1109/IConSCEPT57958.2023.10170387","url":null,"abstract":"Change detection involves quantifying temporal effects with a multi-temporal dataset. Remote sensing data have been extensively utilised for change detection in recent decades. Unsupervised learning is used to analyse satellite imagery or remote sensing data to find changes in land cover or land use over time without the use of labelled training data. Unsupervised learning is a type of machine learning that identifies patterns in data without the use of labels or prior knowledge. The general goal of change detection in remote sensing is to recognise the type of changes in specific geographic locations, and then quantify and assess changes in the regions. In this work, land change detection is analysed using various deep clustering techniques with multitemporal satellite images from different geographical locations. Two models, namely a deep-embedded clustering model, a sparse auto-encoding model are built and trained using both K-Means Clustering and FuzzyC-Means Clustering algorithms in clustering layer. The implemented models address the issue of mixed pixel clustering by using Fuzzy-C Means Clustering to determine whether region has changed over time using satellite images. The implementation is carried out in constrained environment with limited dataset and computational facilities. Deep clustering approaches necessitate high-quality data in order to produce accurate results. Poor-quality data can result in inaccurate clustering results, which can have an impact on the interpretation and application of the results. Due to cloud cover, atmospheric interference, and sensor limitations, environmental data can frequently have issues with noise, missing values, and data gaps, which can impair the quality of the clustering results and in turn, it misleads generation of changed regions. These constraints can have an impact on the quality of the data and make deep clustering approaches difficult to implement. The results of the implemented work have been assessed using Mean Square Error which is a function used to calculate the loss of a model and the effectiveness of a clustering technique is assessed by the silhouette score.","PeriodicalId":240167,"journal":{"name":"2023 International Conference on Signal Processing, Computation, Electronics, Power and Telecommunication (IConSCEPT)","volume":"86 3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127440145","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}
Pub Date : 2023-05-25DOI: 10.1109/IConSCEPT57958.2023.10170000
J. Joshua Alfred, V. Sai Srivathsan, A. Sasithradevi, S. Roomi
Medication error is one of the major causes of death, as victims intake the wrong medicine or dosage which can cause chronic effects. One such cause of medication error comes from the misinterpretation of information due to language barrier. There is a need for translation of information in medicinal strips to create awareness to the user. For this purpose, we propose an Innovative Mobile Application Using Flutter and Dart, empowering all native-Tamil speakers who find difficulty in acquiring information from tablet strips. The app is designed to revolutionize the way people obtain information from tablet strips such as general information, dosage, side effects, etc. with the help of web scraping. With its advanced Optical Character Recognition (OCR) engine, the app can accurately recognize text from images and convert it into editable text. The app’s user-friendly interface with its state-of-art innovation mainly focusing native-Tamil speakers, built using the Flutter framework, allows users to quickly and easily scan and process strings. The application then translates and displays the information present in the Tamil language along with a text-to-speech feature. Upon testing, the application displayed a 90% accuracy in retrieving relevant information about the tablet present in images.
{"title":"MedSay-Tamil: A Pharmacological-Translator Mobile Application for the aid of Native Tamil Speakers","authors":"J. Joshua Alfred, V. Sai Srivathsan, A. Sasithradevi, S. Roomi","doi":"10.1109/IConSCEPT57958.2023.10170000","DOIUrl":"https://doi.org/10.1109/IConSCEPT57958.2023.10170000","url":null,"abstract":"Medication error is one of the major causes of death, as victims intake the wrong medicine or dosage which can cause chronic effects. One such cause of medication error comes from the misinterpretation of information due to language barrier. There is a need for translation of information in medicinal strips to create awareness to the user. For this purpose, we propose an Innovative Mobile Application Using Flutter and Dart, empowering all native-Tamil speakers who find difficulty in acquiring information from tablet strips. The app is designed to revolutionize the way people obtain information from tablet strips such as general information, dosage, side effects, etc. with the help of web scraping. With its advanced Optical Character Recognition (OCR) engine, the app can accurately recognize text from images and convert it into editable text. The app’s user-friendly interface with its state-of-art innovation mainly focusing native-Tamil speakers, built using the Flutter framework, allows users to quickly and easily scan and process strings. The application then translates and displays the information present in the Tamil language along with a text-to-speech feature. Upon testing, the application displayed a 90% accuracy in retrieving relevant information about the tablet present in images.","PeriodicalId":240167,"journal":{"name":"2023 International Conference on Signal Processing, Computation, Electronics, Power and Telecommunication (IConSCEPT)","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127420512","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}
Pub Date : 2023-05-25DOI: 10.1109/IConSCEPT57958.2023.10170093
Narayana Darapaneni, R. Prajeesh, Payel Dutta, Venkat K Pillai, Anirban Karak, A. Paduri
This paper aims to study the research articles related to Covid-19 and provide abstractive summarization on the same, demystifying the myths related to covid-19 as well as finding the possible root cause of hesitation in taking the vaccine. As per the government of India’s official site, as on 20th Jan 2023, 1 billion people have been fully vaccinated out of India’s total population of 1.4 billion. To fully eradicate Covid - 19, which emerged 3 years ago, the entire population needs to be vaccinated, but that’s not the case as people hesitate to get vaccinated due to various articles published in newspapers, social media, etc., the authenticity of which are unknown. In this paper we will try to summarize all the articles, as available in the CORD-19 dataset, using BERT and GPT-2 models. For extractive summarization, BERT models performed well, but there is a scope for improvement in abstractive summarization. Our approach involves utilizing regularization to suppress local similarity while simultaneously promoting global similarity, using the distill-gpt2 version with higher computing resources. We used V100 GPU with 100 computing engines from google collab-pro for faster computation and higher accuracy. The result will elaborate on the Rouge and Bleu score and its relevant significance for summarization.
{"title":"Abstractive Text Summarization Using BERT and GPT-2 Models","authors":"Narayana Darapaneni, R. Prajeesh, Payel Dutta, Venkat K Pillai, Anirban Karak, A. Paduri","doi":"10.1109/IConSCEPT57958.2023.10170093","DOIUrl":"https://doi.org/10.1109/IConSCEPT57958.2023.10170093","url":null,"abstract":"This paper aims to study the research articles related to Covid-19 and provide abstractive summarization on the same, demystifying the myths related to covid-19 as well as finding the possible root cause of hesitation in taking the vaccine. As per the government of India’s official site, as on 20th Jan 2023, 1 billion people have been fully vaccinated out of India’s total population of 1.4 billion. To fully eradicate Covid - 19, which emerged 3 years ago, the entire population needs to be vaccinated, but that’s not the case as people hesitate to get vaccinated due to various articles published in newspapers, social media, etc., the authenticity of which are unknown. In this paper we will try to summarize all the articles, as available in the CORD-19 dataset, using BERT and GPT-2 models. For extractive summarization, BERT models performed well, but there is a scope for improvement in abstractive summarization. Our approach involves utilizing regularization to suppress local similarity while simultaneously promoting global similarity, using the distill-gpt2 version with higher computing resources. We used V100 GPU with 100 computing engines from google collab-pro for faster computation and higher accuracy. The result will elaborate on the Rouge and Bleu score and its relevant significance for summarization.","PeriodicalId":240167,"journal":{"name":"2023 International Conference on Signal Processing, Computation, Electronics, Power and Telecommunication (IConSCEPT)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126423097","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}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：