Pub Date : 2023-04-05DOI: 10.1109/PCEMS58491.2023.10136069
B. Pramodini, D. Chaturvedi
This article presents a compact size Inverted Lshaped antenna for wireless applications like WLAN and commercial WI-FI applications. The proposed design uses Half Mode Substrate Integrated Waveguide (HMSIW) technology to reduce antenna footprint by 50%, achieved by bisecting the fullmode cavity along the magnetic wall. Further, the miniaturization has been achieved by around 25% by introducing an inverted L-shaped slot on the top cladding of the HMSIW cavity. After introducing the slot, the frequency is reduced to 2.45 GHz from 5.3 GHz. Hence, the overall footprint of the antenna has been reduced to 75%. By using the SIW technology, the cavity-backed antenna is realized in a planar form, also it retains the features of the full-mode cavity. The antenna is designed on RT Duroid 5880 with a substrate thickness of 1.575 mm and a dielectric constant of 2.2. The proposed antenna resonates at 2.45 GHz with a fractional bandwidth of 2.6%. The antenna’s directivity is obtained at 4.91 dBi at the operating frequency. The proposed antenna depicts a unidirectional radiation pattern with a front-to-back ratio (FTBR) of 12.75 dBi. The proposed geometry is low-profile, planar, and compact in nature which can be easily integrated into a hand-held device.
{"title":"Miniaturized Inverted L-Shaped Slot Antenna Using HMSIW Technology","authors":"B. Pramodini, D. Chaturvedi","doi":"10.1109/PCEMS58491.2023.10136069","DOIUrl":"https://doi.org/10.1109/PCEMS58491.2023.10136069","url":null,"abstract":"This article presents a compact size Inverted Lshaped antenna for wireless applications like WLAN and commercial WI-FI applications. The proposed design uses Half Mode Substrate Integrated Waveguide (HMSIW) technology to reduce antenna footprint by 50%, achieved by bisecting the fullmode cavity along the magnetic wall. Further, the miniaturization has been achieved by around 25% by introducing an inverted L-shaped slot on the top cladding of the HMSIW cavity. After introducing the slot, the frequency is reduced to 2.45 GHz from 5.3 GHz. Hence, the overall footprint of the antenna has been reduced to 75%. By using the SIW technology, the cavity-backed antenna is realized in a planar form, also it retains the features of the full-mode cavity. The antenna is designed on RT Duroid 5880 with a substrate thickness of 1.575 mm and a dielectric constant of 2.2. The proposed antenna resonates at 2.45 GHz with a fractional bandwidth of 2.6%. The antenna’s directivity is obtained at 4.91 dBi at the operating frequency. The proposed antenna depicts a unidirectional radiation pattern with a front-to-back ratio (FTBR) of 12.75 dBi. The proposed geometry is low-profile, planar, and compact in nature which can be easily integrated into a hand-held device.","PeriodicalId":330870,"journal":{"name":"2023 2nd International Conference on Paradigm Shifts in Communications Embedded Systems, Machine Learning and Signal Processing (PCEMS)","volume":"43 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121963588","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 : 2023-04-05DOI: 10.1109/PCEMS58491.2023.10136051
Abhinav Jha, H. Patil, S. Jindal, Sardar M N Islam
This paper demonstrates the development and evaluation of a multilingual neural machine translation system for Indian languages based on the mT5 transformer, successfully utilized to develop multiple state-of-the-art NLP models. We used the modified Asian Language Treebank multilingual dataset to train the system for developing a Machine Translation model capable of translating text in English, Hindi and Bengali amongst each other. Our system was able to achieve acceptable BLEU scores of over 20 in five of the six language pairs, with the English to Bengali system achieving a maximum BLEU score of 49.87 and the Bengali to English system achieving an average BLEU score of 42.43.
{"title":"Multilingual Indian Language Neural Machine Translation System Using mT5 Transformer","authors":"Abhinav Jha, H. Patil, S. Jindal, Sardar M N Islam","doi":"10.1109/PCEMS58491.2023.10136051","DOIUrl":"https://doi.org/10.1109/PCEMS58491.2023.10136051","url":null,"abstract":"This paper demonstrates the development and evaluation of a multilingual neural machine translation system for Indian languages based on the mT5 transformer, successfully utilized to develop multiple state-of-the-art NLP models. We used the modified Asian Language Treebank multilingual dataset to train the system for developing a Machine Translation model capable of translating text in English, Hindi and Bengali amongst each other. Our system was able to achieve acceptable BLEU scores of over 20 in five of the six language pairs, with the English to Bengali system achieving a maximum BLEU score of 49.87 and the Bengali to English system achieving an average BLEU score of 42.43.","PeriodicalId":330870,"journal":{"name":"2023 2nd International Conference on Paradigm Shifts in Communications Embedded Systems, Machine Learning and Signal Processing (PCEMS)","volume":"169 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121037726","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}
Fake news refers to misleading or fake information spread over the internet or other communication networks. In our paper, we use different machine learning (ML) models and deep learning (DL) models for classifying news as fake or real. The different ML models used are k-nearest neighbor (KNN), random forest (RF), logistic regression, naive Bayes, and DL models like long short-term memory (LSTM), and gated recurrent units (GRU) for prediction. We developed a mechanism that combines the prediction probabilities of ML models and DL models for prediction. We achieved accuracy as high as 0.98 and F1 scores as high as 0.98 using our approach. We also analyze the results of classification using different graphs which give us meaningful insights into the accuracy of the prediction of different models. We use flow charts to demonstrate the flow of our proposed algorithm in the classification of news. The superiority of our model is demonstrated in experimental results.
{"title":"Fake News Identification: An Effective Combined Approach using ML and DL Techniques","authors":"Ayush Anand, Raghavendra Kulkarni, Pragati Agrawal","doi":"10.1109/PCEMS58491.2023.10136087","DOIUrl":"https://doi.org/10.1109/PCEMS58491.2023.10136087","url":null,"abstract":"Fake news refers to misleading or fake information spread over the internet or other communication networks. In our paper, we use different machine learning (ML) models and deep learning (DL) models for classifying news as fake or real. The different ML models used are k-nearest neighbor (KNN), random forest (RF), logistic regression, naive Bayes, and DL models like long short-term memory (LSTM), and gated recurrent units (GRU) for prediction. We developed a mechanism that combines the prediction probabilities of ML models and DL models for prediction. We achieved accuracy as high as 0.98 and F1 scores as high as 0.98 using our approach. We also analyze the results of classification using different graphs which give us meaningful insights into the accuracy of the prediction of different models. We use flow charts to demonstrate the flow of our proposed algorithm in the classification of news. The superiority of our model is demonstrated in experimental results.","PeriodicalId":330870,"journal":{"name":"2023 2nd International Conference on Paradigm Shifts in Communications Embedded Systems, Machine Learning and Signal Processing (PCEMS)","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121372497","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 : 2023-04-05DOI: 10.1109/PCEMS58491.2023.10136106
K. Raju, A. Kavitha, C. Kaitepalli
The 5th generation mobile technology standards have the guts to deliver high data rates, low latency communications, and massive device connectivity. One of the challenge in front of 5G was spectrum usage, this article was presented, different frequency bands allocated to 5G in the range of sub-6GHz and millimeter wave frequencies in various countries and for the efficient distribution of the 5G systems and in order to meet the challenge of spectrum usage, developed a dual wideband three elements MIMO radiating structure capable to operate in sub-6GHz and mm-wave bands. Primarily the single element radiator was designed on 6.4 X 6.4 X 0.25 mm3 dimensioned Rogers/RT duroid substrate with Halloween structure incorporated patch and grounded with wide rectangular slot. The incorporation of Halloween structure was given gain enhancement and wide rectangular slot on ground was given bandwidth enhancement. The single element radiator was resonated in the band 25.18-29.39GHz with the gain of 4. 69dBi. The MIMO antenna structure was developed by extending the dimensions to S.4 X 23. SX0.25mm3, it was capable to operate in dual bands 5.12-5.97GHz and 12.83-40.4GHz with respect to the -10dB return losses and less than -10dB isolation was observed with respect to adjacent radiators. The Maximum gain obtained over the lower band was 6. 7dBi and higher band was 17. 36dBi. The results demonstrated that the presented antenna structure is well suitable for 5G Applications.
第五代移动技术标准能够提供高数据速率、低延迟通信和大规模设备连接。5G面临的挑战之一是频谱使用，本文介绍了各国在sub-6GHz和毫米波频率范围内分配给5G的不同频段，为了5G系统的有效分布和应对频谱使用的挑战，开发了一种能够在sub-6GHz和mm波段工作的双宽带三元MIMO辐射结构。单元件散热器主要设计在尺寸为6.4 X 6.4 X 0.25 mm3的Rogers/RT duroid基片上，采用万圣节结构，并采用宽矩形槽接地。采用万圣节结构增强增益，地面宽矩形槽增强带宽。单单元辐射器谐振在25.18 ~ 29.39 ghz频段，增益为4。69 dbi。MIMO天线结构是通过将尺寸扩展到S.4 X . 23而开发的。SX0.25mm3，它能够在5.12-5.97GHz和12.83-40.4GHz双频段工作，相对于-10dB的回波损耗，并且相对于相邻的散热器观察到小于-10dB的隔离。下波段获得的最大增益为6。7dBi及以上波段为17。36 dbi。结果表明，该天线结构非常适合5G应用。
{"title":"Halloween Structured Microstrip MIMO Radiator at 5G sub-6GHz and mm-wave Frequencies","authors":"K. Raju, A. Kavitha, C. Kaitepalli","doi":"10.1109/PCEMS58491.2023.10136106","DOIUrl":"https://doi.org/10.1109/PCEMS58491.2023.10136106","url":null,"abstract":"The 5th generation mobile technology standards have the guts to deliver high data rates, low latency communications, and massive device connectivity. One of the challenge in front of 5G was spectrum usage, this article was presented, different frequency bands allocated to 5G in the range of sub-6GHz and millimeter wave frequencies in various countries and for the efficient distribution of the 5G systems and in order to meet the challenge of spectrum usage, developed a dual wideband three elements MIMO radiating structure capable to operate in sub-6GHz and mm-wave bands. Primarily the single element radiator was designed on 6.4 X 6.4 X 0.25 mm3 dimensioned Rogers/RT duroid substrate with Halloween structure incorporated patch and grounded with wide rectangular slot. The incorporation of Halloween structure was given gain enhancement and wide rectangular slot on ground was given bandwidth enhancement. The single element radiator was resonated in the band 25.18-29.39GHz with the gain of 4. 69dBi. The MIMO antenna structure was developed by extending the dimensions to S.4 X 23. SX0.25mm3, it was capable to operate in dual bands 5.12-5.97GHz and 12.83-40.4GHz with respect to the -10dB return losses and less than -10dB isolation was observed with respect to adjacent radiators. The Maximum gain obtained over the lower band was 6. 7dBi and higher band was 17. 36dBi. The results demonstrated that the presented antenna structure is well suitable for 5G Applications.","PeriodicalId":330870,"journal":{"name":"2023 2nd International Conference on Paradigm Shifts in Communications Embedded Systems, Machine Learning and Signal Processing (PCEMS)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128609593","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 : 2023-04-05DOI: 10.1109/PCEMS58491.2023.10136113
Md. Helal Manzoor, Abhishek Ray, Alok Naugarhiya
A 40 nm long channel FinFET-based biosensor has been demonstrated. A cavity is created to provide a biomolecule detecting surface. For immobilization, biomolecules are injected into cavities and nanocavities. Silvaco ATLAS device simulator tool has been used to examine the electrical properties of the device, including threshold voltage, transfer characteristics, switching ratio, subthreshold swing, and transconductance. Various biomolecules such as uricase, biotin, keratin are used for examining the sensitivity of the biosensor. The sensitivity of the biosensor is used to measure its detecting capacity. The likelihood of detecting biomolecules increases with increasing sensitivity. A biomolecule’s electrical properties are contrasted with the cavity’s empty space.
{"title":"Analysis of GaAs FinFET Based Biosensor with Under Gate Cavity","authors":"Md. Helal Manzoor, Abhishek Ray, Alok Naugarhiya","doi":"10.1109/PCEMS58491.2023.10136113","DOIUrl":"https://doi.org/10.1109/PCEMS58491.2023.10136113","url":null,"abstract":"A 40 nm long channel FinFET-based biosensor has been demonstrated. A cavity is created to provide a biomolecule detecting surface. For immobilization, biomolecules are injected into cavities and nanocavities. Silvaco ATLAS device simulator tool has been used to examine the electrical properties of the device, including threshold voltage, transfer characteristics, switching ratio, subthreshold swing, and transconductance. Various biomolecules such as uricase, biotin, keratin are used for examining the sensitivity of the biosensor. The sensitivity of the biosensor is used to measure its detecting capacity. The likelihood of detecting biomolecules increases with increasing sensitivity. A biomolecule’s electrical properties are contrasted with the cavity’s empty space.","PeriodicalId":330870,"journal":{"name":"2023 2nd International Conference on Paradigm Shifts in Communications Embedded Systems, Machine Learning and Signal Processing (PCEMS)","volume":"106 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122681889","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 : 2023-04-05DOI: 10.1109/PCEMS58491.2023.10136052
Uma Maheswara Rao Ukyam, Panchadi Sireesha, Pailla Durga Pavan Kumar, Addala P N V R Manikanta Ashish, K. Gurrala
In this paper, the secrecy rate of reconfigurable intelligent surface (RIS) aided wireless networks with one eavesdropper around is investigated. In the system model, the source broadcasts the signal to the destination via an intermediate node RIS, and the controlling Jammer (CJ) near to the eavesdropper ensures physical layer security. Our major objective is to increase the secrecy rate by distributing power optimally between the source and the jammer. By using the Lagrange’s multiplier approach, we devised a power allocation strategy and found the optimum power distribution coefficient for distributing power between the source and the jammer. Our results demonstrate that the secrecy rate of the system model with controlling Jammer is superior to that of the system model with Jammer, the system model without Jammer and that the optimal distribution of power (ODP) has a higher secrecy rate than the equal distribution of power (EDP).
{"title":"Enhanced Physical Layer Security for RIS aided Wireless Network with Control Jammer and Power Allocation Scheme","authors":"Uma Maheswara Rao Ukyam, Panchadi Sireesha, Pailla Durga Pavan Kumar, Addala P N V R Manikanta Ashish, K. Gurrala","doi":"10.1109/PCEMS58491.2023.10136052","DOIUrl":"https://doi.org/10.1109/PCEMS58491.2023.10136052","url":null,"abstract":"In this paper, the secrecy rate of reconfigurable intelligent surface (RIS) aided wireless networks with one eavesdropper around is investigated. In the system model, the source broadcasts the signal to the destination via an intermediate node RIS, and the controlling Jammer (CJ) near to the eavesdropper ensures physical layer security. Our major objective is to increase the secrecy rate by distributing power optimally between the source and the jammer. By using the Lagrange’s multiplier approach, we devised a power allocation strategy and found the optimum power distribution coefficient for distributing power between the source and the jammer. Our results demonstrate that the secrecy rate of the system model with controlling Jammer is superior to that of the system model with Jammer, the system model without Jammer and that the optimal distribution of power (ODP) has a higher secrecy rate than the equal distribution of power (EDP).","PeriodicalId":330870,"journal":{"name":"2023 2nd International Conference on Paradigm Shifts in Communications Embedded Systems, Machine Learning and Signal Processing (PCEMS)","volume":"106 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124695032","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 : 2023-04-05DOI: 10.1109/PCEMS58491.2023.10136120
Baloju Revanth, Sakshi Gupta, Prakhar Dubey, B. Choudhury, Kranti S. Kamble, Joydeep Sengupta
Electroencephalogram (EEG)-based emotion recognition has demonstrated encouraging results using machine learning (ML)-based algorithms. This study compares the performance of different frequency bands using four ML-based classifiers for the recognition of multi-class human emotions from EEG signals. Initially, the raw EEG signals are divided into five frequency bands such as delta, theta, alpha, beta, and gamma bands. Secondly, the statistical, time and frequency domain features are extracted. To classify emotions into positive, negative and neutral classes from the SEED dataset, these features are fed to four ML-based classifiers. This study shows the efficacy of an ensemble ML-based classifier over traditional classifiers. The best highest average classification accuracy reported by the random forest (RF) classifier for the delta band is 95.71%. The second highest average accuracy was reported by KNN with 80.32% for the theta band. A similar trend was also followed by other frequency bands. In conclusion, our study demonstrated the value of the proposed ML-based model for multi-class emotion recognition.
{"title":"Multi-Channel EEG-based Multi-Class Emotion Recognition From Multiple Frequency Bands","authors":"Baloju Revanth, Sakshi Gupta, Prakhar Dubey, B. Choudhury, Kranti S. Kamble, Joydeep Sengupta","doi":"10.1109/PCEMS58491.2023.10136120","DOIUrl":"https://doi.org/10.1109/PCEMS58491.2023.10136120","url":null,"abstract":"Electroencephalogram (EEG)-based emotion recognition has demonstrated encouraging results using machine learning (ML)-based algorithms. This study compares the performance of different frequency bands using four ML-based classifiers for the recognition of multi-class human emotions from EEG signals. Initially, the raw EEG signals are divided into five frequency bands such as delta, theta, alpha, beta, and gamma bands. Secondly, the statistical, time and frequency domain features are extracted. To classify emotions into positive, negative and neutral classes from the SEED dataset, these features are fed to four ML-based classifiers. This study shows the efficacy of an ensemble ML-based classifier over traditional classifiers. The best highest average classification accuracy reported by the random forest (RF) classifier for the delta band is 95.71%. The second highest average accuracy was reported by KNN with 80.32% for the theta band. A similar trend was also followed by other frequency bands. In conclusion, our study demonstrated the value of the proposed ML-based model for multi-class emotion recognition.","PeriodicalId":330870,"journal":{"name":"2023 2nd International Conference on Paradigm Shifts in Communications Embedded Systems, Machine Learning and Signal Processing (PCEMS)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125294601","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 : 2023-04-05DOI: 10.1109/PCEMS58491.2023.10136040
Indrani Vejalla, Sai Preethi Battula, Kartheek Kalluri, H. Kalluri
There are many types of fraud in our daily life. One of the frauds occurring these days is credit card fraud. When people around the globe make credit card transactions, there will also be fraudulent transactions. To avoid credit card fraud, we must know the patterns and how the fraud values differ. This paper proposed credit card fraud detection using machine learning based on the labeled data and differentiating the fraudulent and legitimate transactions. The experiment was conducted using supervised machine-learning techniques.
{"title":"Credit Card Fraud Detection Using Machine Learning Techniques","authors":"Indrani Vejalla, Sai Preethi Battula, Kartheek Kalluri, H. Kalluri","doi":"10.1109/PCEMS58491.2023.10136040","DOIUrl":"https://doi.org/10.1109/PCEMS58491.2023.10136040","url":null,"abstract":"There are many types of fraud in our daily life. One of the frauds occurring these days is credit card fraud. When people around the globe make credit card transactions, there will also be fraudulent transactions. To avoid credit card fraud, we must know the patterns and how the fraud values differ. This paper proposed credit card fraud detection using machine learning based on the labeled data and differentiating the fraudulent and legitimate transactions. The experiment was conducted using supervised machine-learning techniques.","PeriodicalId":330870,"journal":{"name":"2023 2nd International Conference on Paradigm Shifts in Communications Embedded Systems, Machine Learning and Signal Processing (PCEMS)","volume":"294 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123115767","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 : 2023-04-05DOI: 10.1109/PCEMS58491.2023.10136099
Givari Santhosh, A. S. Raghuvanshi
Power has a notable influence on the functionality and reliability of the Very Large-Scale Integration (VLSI) circuits. Thus, estimation of consumed power at an initial phase is extremely necessary. This paper describes the comparative study of supervised ensemble based boosting machine learning techniques to predict synchronous sequential VLSI circuits. We implemented three supervised ensemble based boosting learning algorithms for power estimation: Adaptive Boosting (AdaBoost), Gradient Boosting (GB) and Extreme Gradient Boosting (XgBoost). Ensemble boosting techniques are tuned by using Grid Search and Random Search hyper-parameter optimization techniques. The ensemble based boosting techniques are applied on IEEE ISCAS’89 benchmark circuits. The coefficient of determination (R) and Root Mean Squared Error (RMSE) are the statistical parameters. These statistical parameters are calculated for each boosting algorithm. The experimental results show that gradient boosting with grid search hyper-parameter optimization approach is a strong preference for predicting the power of synchronous sequential VLSI circuits. Since it has remarkable coefficient of determination of 0.99746 and lower RMSE of 3.143e-5.
{"title":"Power Estimation of Synchronous Sequential VLSI Circuits Using Boosting Techniques","authors":"Givari Santhosh, A. S. Raghuvanshi","doi":"10.1109/PCEMS58491.2023.10136099","DOIUrl":"https://doi.org/10.1109/PCEMS58491.2023.10136099","url":null,"abstract":"Power has a notable influence on the functionality and reliability of the Very Large-Scale Integration (VLSI) circuits. Thus, estimation of consumed power at an initial phase is extremely necessary. This paper describes the comparative study of supervised ensemble based boosting machine learning techniques to predict synchronous sequential VLSI circuits. We implemented three supervised ensemble based boosting learning algorithms for power estimation: Adaptive Boosting (AdaBoost), Gradient Boosting (GB) and Extreme Gradient Boosting (XgBoost). Ensemble boosting techniques are tuned by using Grid Search and Random Search hyper-parameter optimization techniques. The ensemble based boosting techniques are applied on IEEE ISCAS’89 benchmark circuits. The coefficient of determination (R) and Root Mean Squared Error (RMSE) are the statistical parameters. These statistical parameters are calculated for each boosting algorithm. The experimental results show that gradient boosting with grid search hyper-parameter optimization approach is a strong preference for predicting the power of synchronous sequential VLSI circuits. Since it has remarkable coefficient of determination of 0.99746 and lower RMSE of 3.143e-5.","PeriodicalId":330870,"journal":{"name":"2023 2nd International Conference on Paradigm Shifts in Communications Embedded Systems, Machine Learning and Signal Processing (PCEMS)","volume":"46 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120978189","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 : 2023-04-05DOI: 10.1109/PCEMS58491.2023.10136085
Vilas Kisanrao Tembhurne, Vinayak D. Shinde, Santosh Kumar, M. Shrimali, Gunjan Chhabra, M. Quadri, Vikram Rajpoot
Air pollution (AP) is today’s most pressing issue. Particularly concerning are the potential adverse effects that an excessive amount of certain hazardous gases, such as CO, SO2, particulate matter, and several others, may have on human health. Other environmental gases are affected by temperature, humidity, etc., wind speed, and their causes and impacts. These weather factors include temperature, humidity, as well as wind speed.For this project, a centralized cloud-based system using sensors that monitor and analyze AP will be developed. The information gathered by each sensor node is uploaded to a cloud server, where it is stored and can be viewed through a web browser at any time and from any location. Because the environment is being monitored in real-time, prompt action may be performed in response to discovering a contaminant in the ecosystem. This project aims to monitor the AP of the surrounding area and ensure that data are kept up to date on the internet. Readings are conducted continuously throughout the day and in real-time. Many air pollutants like SO2, CO, PM10, humidity, and temperature are considered to measure air quality by IoT-based air pollution monitoring systems (APMS). We created graphics that simplify analyzing the proportion of pollutants in a certain location. The LCD can show the gas sensor’s real-time data constantly.
{"title":"IoT-based Air Pollution Monitoring System to Measure Air Quality on Cloud Storage","authors":"Vilas Kisanrao Tembhurne, Vinayak D. Shinde, Santosh Kumar, M. Shrimali, Gunjan Chhabra, M. Quadri, Vikram Rajpoot","doi":"10.1109/PCEMS58491.2023.10136085","DOIUrl":"https://doi.org/10.1109/PCEMS58491.2023.10136085","url":null,"abstract":"Air pollution (AP) is today’s most pressing issue. Particularly concerning are the potential adverse effects that an excessive amount of certain hazardous gases, such as CO, SO2, particulate matter, and several others, may have on human health. Other environmental gases are affected by temperature, humidity, etc., wind speed, and their causes and impacts. These weather factors include temperature, humidity, as well as wind speed.For this project, a centralized cloud-based system using sensors that monitor and analyze AP will be developed. The information gathered by each sensor node is uploaded to a cloud server, where it is stored and can be viewed through a web browser at any time and from any location. Because the environment is being monitored in real-time, prompt action may be performed in response to discovering a contaminant in the ecosystem. This project aims to monitor the AP of the surrounding area and ensure that data are kept up to date on the internet. Readings are conducted continuously throughout the day and in real-time. Many air pollutants like SO2, CO, PM10, humidity, and temperature are considered to measure air quality by IoT-based air pollution monitoring systems (APMS). We created graphics that simplify analyzing the proportion of pollutants in a certain location. The LCD can show the gas sensor’s real-time data constantly.","PeriodicalId":330870,"journal":{"name":"2023 2nd International Conference on Paradigm Shifts in Communications Embedded Systems, Machine Learning and Signal Processing (PCEMS)","volume":"57 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132172042","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：