Pub Date : 2022-03-24DOI: 10.1109/wispnet54241.2022.9767169
Shayna Kumari, S. Prince
In this paper, $1 times 8 s-text{bend}-text{arc}$ based symmetrical and wavelength insensitive optical beam splitter is modeled using beam propagation method (BPM). Silicon-on-insulator (SOI) material platform is utilized for realizing rib structure based single-mode linear and $s$-bend curve waveguides. The performance of splitter is characterized in terms of insertion loss and non-uniformity (insertion loss uniformity). The proposed device provides spectral flatness over 100 nm wavelength span ranging from 1500 nm to 1600 nm. Also, 95.3 % of relative power is observed at the output waveguide port of the device.
{"title":"Broadband Planar Waveguide Power Splitter Based on Symmetrical S-bends","authors":"Shayna Kumari, S. Prince","doi":"10.1109/wispnet54241.2022.9767169","DOIUrl":"https://doi.org/10.1109/wispnet54241.2022.9767169","url":null,"abstract":"In this paper, $1 times 8 s-text{bend}-text{arc}$ based symmetrical and wavelength insensitive optical beam splitter is modeled using beam propagation method (BPM). Silicon-on-insulator (SOI) material platform is utilized for realizing rib structure based single-mode linear and $s$-bend curve waveguides. The performance of splitter is characterized in terms of insertion loss and non-uniformity (insertion loss uniformity). The proposed device provides spectral flatness over 100 nm wavelength span ranging from 1500 nm to 1600 nm. Also, 95.3 % of relative power is observed at the output waveguide port of the device.","PeriodicalId":432794,"journal":{"name":"2022 International Conference on Wireless Communications Signal Processing and Networking (WiSPNET)","volume":"56 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130078355","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 : 2022-03-24DOI: 10.1109/wispnet54241.2022.9767102
S. G., C. P, Umamaheswari Rajasekaran
Deep neural networks have been used successfully to solve time series prediction problems. Given their ability to automatically understand the temporal connections found in time series, they have shown to be an effective solution. In this proposed research, a Deep Learning (DL) based flood prediction model is explored and utilized for interpretation and prediction using meteorological data to reduce computational and time complexity with high accuracy. Gated Recurrent Networks (GRU) a variant of recurrent neural network model which can effectively use past data information for prediction and is faster in terms of training speed is the deep learning architecture deployed. Correlation analysis was performed on the weather parameters and the appropriate parameters were chosen. The dataset compromises 52 years (19022 records) of weather data in which 80% is used for training 20% for testing. The predictive modeling of rainfall associated with the South-west monsoon can guide the prediction of flood occurrence. The model deployed was evaluated with the performance metrics such as RMSE, MAE against LSTM model. The deployed RNN-GRU model had relatively low RMSE and MAE values when compared with LSTM architecture with improved prediction accuracy.
{"title":"Time-series analysis and Flood Prediction using a Deep Learning Approach","authors":"S. G., C. P, Umamaheswari Rajasekaran","doi":"10.1109/wispnet54241.2022.9767102","DOIUrl":"https://doi.org/10.1109/wispnet54241.2022.9767102","url":null,"abstract":"Deep neural networks have been used successfully to solve time series prediction problems. Given their ability to automatically understand the temporal connections found in time series, they have shown to be an effective solution. In this proposed research, a Deep Learning (DL) based flood prediction model is explored and utilized for interpretation and prediction using meteorological data to reduce computational and time complexity with high accuracy. Gated Recurrent Networks (GRU) a variant of recurrent neural network model which can effectively use past data information for prediction and is faster in terms of training speed is the deep learning architecture deployed. Correlation analysis was performed on the weather parameters and the appropriate parameters were chosen. The dataset compromises 52 years (19022 records) of weather data in which 80% is used for training 20% for testing. The predictive modeling of rainfall associated with the South-west monsoon can guide the prediction of flood occurrence. The model deployed was evaluated with the performance metrics such as RMSE, MAE against LSTM model. The deployed RNN-GRU model had relatively low RMSE and MAE values when compared with LSTM architecture with improved prediction accuracy.","PeriodicalId":432794,"journal":{"name":"2022 International Conference on Wireless Communications Signal Processing and Networking (WiSPNET)","volume":"78 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130478684","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 : 2022-03-24DOI: 10.1109/wispnet54241.2022.9767127
B. P, R. M.
In this paper, we describe the collection of speech samples to develop a database for speaker recognition in the Indian scenario in the office environment and named VIT-Indian Language Speech Corpus (VIT-ILSC) speech database. Presently, we developed the Phase −1 database of speech samples from 50 speakers. The speech samples were collected in the office environment. Most of the speech samples collected are in English and other Indian languages in reading style, using two digital voice recorders. This work aims to develop a speech corpus database for a speaker recognition system in Indian languages, including English. Traditional Mel-frequency cepstral coefficients (MFCC) and Gaussian Mixture Model (GMM) was used to evaluate the collected phase-1 database. The phase-1 database has been evaluated on a speaker verification system. We considered both clean and noise backgrounds for initial studies and showed the impact of mismatch in training and testing samples.
{"title":"Development of Multilingual Speech Database for Speaker Recognition in Indian Languages","authors":"B. P, R. M.","doi":"10.1109/wispnet54241.2022.9767127","DOIUrl":"https://doi.org/10.1109/wispnet54241.2022.9767127","url":null,"abstract":"In this paper, we describe the collection of speech samples to develop a database for speaker recognition in the Indian scenario in the office environment and named VIT-Indian Language Speech Corpus (VIT-ILSC) speech database. Presently, we developed the Phase −1 database of speech samples from 50 speakers. The speech samples were collected in the office environment. Most of the speech samples collected are in English and other Indian languages in reading style, using two digital voice recorders. This work aims to develop a speech corpus database for a speaker recognition system in Indian languages, including English. Traditional Mel-frequency cepstral coefficients (MFCC) and Gaussian Mixture Model (GMM) was used to evaluate the collected phase-1 database. The phase-1 database has been evaluated on a speaker verification system. We considered both clean and noise backgrounds for initial studies and showed the impact of mismatch in training and testing samples.","PeriodicalId":432794,"journal":{"name":"2022 International Conference on Wireless Communications Signal Processing and Networking (WiSPNET)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115954539","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}
We consider the cooperative spectrum sensing problem in cognitive radios as a deep learning-based classification problem, under generalized fading scenarios. In particular, we carry out a performance comparison of well-known deep learning architectures such as deep neural networks, convolutional neural networks (CNN), long short term memory (LSTM) networks, CNN-LSTM networks and gated recurrent units (GRU). The features selected are maximum eigenvalue, energy statistic and maximum-minimum eigenvalue of the received sample correlation matrix. Through experimental studies, we show that GRU marginally outperforms other architectures, and usage of the maximum eigenvalue feature yields the best performance in terms of classification accuracy. Further, the variation in the accuracy performance of the GRU architecture with parameters such as the number of sensors, number of observations and fading parameters are discussed.
{"title":"Deep Learning Techniques for Cooperative Spectrum Sensing Under Generalized Fading Channels","authors":"Pradeep Balaji Muthukumar, Samudhyatha B., Sanjeev Gurugopinath","doi":"10.1109/wispnet54241.2022.9767160","DOIUrl":"https://doi.org/10.1109/wispnet54241.2022.9767160","url":null,"abstract":"We consider the cooperative spectrum sensing problem in cognitive radios as a deep learning-based classification problem, under generalized fading scenarios. In particular, we carry out a performance comparison of well-known deep learning architectures such as deep neural networks, convolutional neural networks (CNN), long short term memory (LSTM) networks, CNN-LSTM networks and gated recurrent units (GRU). The features selected are maximum eigenvalue, energy statistic and maximum-minimum eigenvalue of the received sample correlation matrix. Through experimental studies, we show that GRU marginally outperforms other architectures, and usage of the maximum eigenvalue feature yields the best performance in terms of classification accuracy. Further, the variation in the accuracy performance of the GRU architecture with parameters such as the number of sensors, number of observations and fading parameters are discussed.","PeriodicalId":432794,"journal":{"name":"2022 International Conference on Wireless Communications Signal Processing and Networking (WiSPNET)","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133672827","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 : 2022-03-24DOI: 10.1109/wispnet54241.2022.9767155
Thennarasi Govindan, S. Palaniswamy, M. Kanagasabai, Sachin Kumar, R. T., Lekha Kannappan
A hexagon shaped four-port ultra-wideband (UWB) MIMO antenna is proposed for WBAN application. The substrate used is Rogers 5870 which is flexible and biocompatible. The single antenna's and MIMO antenna's total layouts are $28 times 25times 0.76$ cubic millimeter and $58 times 58times 0.76$ cubic millimeter. The diversity parameters like $text{ECC} < 0.1, text{DG} > 9.6$ dB, $text{CCL}< 0.2$ bits/s/Hz and $text{TARC} <-12 text{dB}$ are calculated. The proposed antenna's maximum gain and efficiency are 3.957 dBi and 98.5% respectively. To guarantee that the proposed antenna does not expose human tissues to radiation, a specific absorption rate (SAR) analysis is assisted. For 1 gram of tissue, SAR values of $0.513 W/Kg$ is obtained at 4 GHz and 0.316 W/kg is achieved at 8 GHz.
{"title":"Hexagon Shaped UWB Monopole MIMO Antenna for WBAN Applications","authors":"Thennarasi Govindan, S. Palaniswamy, M. Kanagasabai, Sachin Kumar, R. T., Lekha Kannappan","doi":"10.1109/wispnet54241.2022.9767155","DOIUrl":"https://doi.org/10.1109/wispnet54241.2022.9767155","url":null,"abstract":"A hexagon shaped four-port ultra-wideband (UWB) MIMO antenna is proposed for WBAN application. The substrate used is Rogers 5870 which is flexible and biocompatible. The single antenna's and MIMO antenna's total layouts are $28 times 25times 0.76$ cubic millimeter and $58 times 58times 0.76$ cubic millimeter. The diversity parameters like $text{ECC} < 0.1, text{DG} > 9.6$ dB, $text{CCL}< 0.2$ bits/s/Hz and $text{TARC} <-12 text{dB}$ are calculated. The proposed antenna's maximum gain and efficiency are 3.957 dBi and 98.5% respectively. To guarantee that the proposed antenna does not expose human tissues to radiation, a specific absorption rate (SAR) analysis is assisted. For 1 gram of tissue, SAR values of $0.513 W/Kg$ is obtained at 4 GHz and 0.316 W/kg is achieved at 8 GHz.","PeriodicalId":432794,"journal":{"name":"2022 International Conference on Wireless Communications Signal Processing and Networking (WiSPNET)","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125160009","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 : 2022-03-24DOI: 10.1109/wispnet54241.2022.9767183
A. S., G. K, Premaladha J., N. V
This paper suggests a novel diversion in color medical image encryption using a chaotic framework and Advanced Encryption Standard AES with Poisson regression model. Nowa-days, the remote healthcare monitoring application is getting prominent by providing better assistance to people's life. We proposed a secure color image encryption algorithm for the medical images using the 2D Arnold cat map, AES-128 and Poisson regression. The workflow explained sequentially in this way. First, the plain medical image is decoupled into the corresponding RGB channels. Next, the chaotic map is applied to the plain image for converting it into a scrambled one. This scrambled image is transmitted to the AES-128 encryption block which converts the scrambled image into the encoded text form and encrypted using the hashed symmetric Key. Then the Encrypted image is formed through the Poisson regression model to predict the pixels based on the text encrypted. Finally, the resultant image is transmitted to the receiver with the NPCR score of 99.0174 and average UACI score of 33.0690. The results for the experimental work and its formulated security analyses reveal that this image encryption technique is applicable for medical image encryption and transmission.
{"title":"Medical Color Image Encryption Using Chaotic Framework and AES Through Poisson Regression Model","authors":"A. S., G. K, Premaladha J., N. V","doi":"10.1109/wispnet54241.2022.9767183","DOIUrl":"https://doi.org/10.1109/wispnet54241.2022.9767183","url":null,"abstract":"This paper suggests a novel diversion in color medical image encryption using a chaotic framework and Advanced Encryption Standard AES with Poisson regression model. Nowa-days, the remote healthcare monitoring application is getting prominent by providing better assistance to people's life. We proposed a secure color image encryption algorithm for the medical images using the 2D Arnold cat map, AES-128 and Poisson regression. The workflow explained sequentially in this way. First, the plain medical image is decoupled into the corresponding RGB channels. Next, the chaotic map is applied to the plain image for converting it into a scrambled one. This scrambled image is transmitted to the AES-128 encryption block which converts the scrambled image into the encoded text form and encrypted using the hashed symmetric Key. Then the Encrypted image is formed through the Poisson regression model to predict the pixels based on the text encrypted. Finally, the resultant image is transmitted to the receiver with the NPCR score of 99.0174 and average UACI score of 33.0690. The results for the experimental work and its formulated security analyses reveal that this image encryption technique is applicable for medical image encryption and transmission.","PeriodicalId":432794,"journal":{"name":"2022 International Conference on Wireless Communications Signal Processing and Networking (WiSPNET)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129655942","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 : 2022-03-24DOI: 10.1109/wispnet54241.2022.9767144
Supritha M. Shetty, Heena M Shirahatti, Ujwala Patil, Deepak K. T.
Voice activity detection (VAD) plays an important role as a pre-processing block in many speech processing applications like speech coding, speech enhancement, speech recognition systems, etc. The main objective of VAD algorithm is to identify speech and non-speech regions in a given audio signal. However the challenging task for the VAD systems would be classifying speech/non-speech frames in an input audio signal that are corrupted by noise i.e environmental noise. With a view to address such a problem, we propose a new approach to VAD using a deep generative model. These models have the ability to learn the underlying distribution of target data through adversarial learning process. In this work, we explore Speech Enhancement GAN (SEGAN) which is a variant of GAN, to analyze the VAD application. The proposed work is evaluated on a subset of Apollo speech corpus as the dataset contain speech files with multiple challenges such as multiple speakers with different noise types, different Signal-to-Noise Ratio (SNR) levels, channel distortion and non-speech for a long duration. The performance of the system is evaluated using detection cost function(DCF) metric. The proposed work gives a better result when compared to other state-of-the-art methods.
{"title":"Voice Activity Detection Through Adversarial Learning","authors":"Supritha M. Shetty, Heena M Shirahatti, Ujwala Patil, Deepak K. T.","doi":"10.1109/wispnet54241.2022.9767144","DOIUrl":"https://doi.org/10.1109/wispnet54241.2022.9767144","url":null,"abstract":"Voice activity detection (VAD) plays an important role as a pre-processing block in many speech processing applications like speech coding, speech enhancement, speech recognition systems, etc. The main objective of VAD algorithm is to identify speech and non-speech regions in a given audio signal. However the challenging task for the VAD systems would be classifying speech/non-speech frames in an input audio signal that are corrupted by noise i.e environmental noise. With a view to address such a problem, we propose a new approach to VAD using a deep generative model. These models have the ability to learn the underlying distribution of target data through adversarial learning process. In this work, we explore Speech Enhancement GAN (SEGAN) which is a variant of GAN, to analyze the VAD application. The proposed work is evaluated on a subset of Apollo speech corpus as the dataset contain speech files with multiple challenges such as multiple speakers with different noise types, different Signal-to-Noise Ratio (SNR) levels, channel distortion and non-speech for a long duration. The performance of the system is evaluated using detection cost function(DCF) metric. The proposed work gives a better result when compared to other state-of-the-art methods.","PeriodicalId":432794,"journal":{"name":"2022 International Conference on Wireless Communications Signal Processing and Networking (WiSPNET)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130197503","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 : 2022-03-24DOI: 10.1109/wispnet54241.2022.9767174
U. M, P. A, V. V, Swarnalatha M.
Depression or emotion is the most important concern of health organizations today. We consider the capability of influencing social media postings as a new type of mirror in understanding depression and also the type of personality in populations. Social network analysis is the study of a group of people and the relationships that exist between them. It has become so important in our lives that if I want to know anything about a stranger, I can find out with the help of social media websites. The arrival of various social media networking sites has helped everyone to easily express and share their opinions and feelings about anything with millions of people around the world. Social media is a valuable resource for identifying an individual's personality traits based on their posts, comments, or activities on social media. The proposed methodology, we have developed the application of a web extension to connect with social media networks to extract the post by the individual person. Extracted post has been used to identify the emotional stability of a person. NLP and Machine Learning algorithms are used to classify individual emotional stability as stable, depressed, or tending towards depression. According to our study, significant feature selections and their combinations were considered. Hence it improves the performance and accuracy of classification.
{"title":"Analyzing Emotional Stability on Social Media Post using Machine Learning Approach","authors":"U. M, P. A, V. V, Swarnalatha M.","doi":"10.1109/wispnet54241.2022.9767174","DOIUrl":"https://doi.org/10.1109/wispnet54241.2022.9767174","url":null,"abstract":"Depression or emotion is the most important concern of health organizations today. We consider the capability of influencing social media postings as a new type of mirror in understanding depression and also the type of personality in populations. Social network analysis is the study of a group of people and the relationships that exist between them. It has become so important in our lives that if I want to know anything about a stranger, I can find out with the help of social media websites. The arrival of various social media networking sites has helped everyone to easily express and share their opinions and feelings about anything with millions of people around the world. Social media is a valuable resource for identifying an individual's personality traits based on their posts, comments, or activities on social media. The proposed methodology, we have developed the application of a web extension to connect with social media networks to extract the post by the individual person. Extracted post has been used to identify the emotional stability of a person. NLP and Machine Learning algorithms are used to classify individual emotional stability as stable, depressed, or tending towards depression. According to our study, significant feature selections and their combinations were considered. Hence it improves the performance and accuracy of classification.","PeriodicalId":432794,"journal":{"name":"2022 International Conference on Wireless Communications Signal Processing and Networking (WiSPNET)","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126911981","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 : 2022-03-24DOI: 10.1109/wispnet54241.2022.9767129
M.C.P. Archana, J. V. Panicker
Cervical intraepithelial neoplasia (CIN) is a major problem women face worldwide. The classic Pap smear analysis (Papanicolaou) is a suitable method for assessing cell images to diagnose cervical disorders. Many computer vision algorithms may be utilized to identify the cancerous and non-cancerous pap smear cell images. The majority of existing research focuses on binary classification techniques that use different methods. However, they have intrinsic difficulties with the excision of minor features and exact categorization. We propose a novel approach for performing multiclass classification of cervical cells with optimal feature extraction, minimal parameters, and less computing power than competing models. The implementation of ConvNet with the Transfer Learning approach validates significant cancer cell diagnosis. The suggested binary and multiclass classification techniques obtained 99.3% and 97.3% accuracy results, respectively, on the dataset.
{"title":"Deep Convolutional Neural Networks for Multiclass Cervical Cell Classification","authors":"M.C.P. Archana, J. V. Panicker","doi":"10.1109/wispnet54241.2022.9767129","DOIUrl":"https://doi.org/10.1109/wispnet54241.2022.9767129","url":null,"abstract":"Cervical intraepithelial neoplasia (CIN) is a major problem women face worldwide. The classic Pap smear analysis (Papanicolaou) is a suitable method for assessing cell images to diagnose cervical disorders. Many computer vision algorithms may be utilized to identify the cancerous and non-cancerous pap smear cell images. The majority of existing research focuses on binary classification techniques that use different methods. However, they have intrinsic difficulties with the excision of minor features and exact categorization. We propose a novel approach for performing multiclass classification of cervical cells with optimal feature extraction, minimal parameters, and less computing power than competing models. The implementation of ConvNet with the Transfer Learning approach validates significant cancer cell diagnosis. The suggested binary and multiclass classification techniques obtained 99.3% and 97.3% accuracy results, respectively, on the dataset.","PeriodicalId":432794,"journal":{"name":"2022 International Conference on Wireless Communications Signal Processing and Networking (WiSPNET)","volume":"74 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133611232","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 : 2022-03-24DOI: 10.1109/wispnet54241.2022.9767107
Sahana Rangasrinivasan, Sri Lohitha Bhagam, Nair K. Athira, Kondapi Niharika, Anjuna D. Raj, T. Anjali
The COVID-19 pandemic has led to many lifestyle changes, one of them being the mandatory use of face masks in public settings. Given the importance of masks, there are various types for people to use, such as cloth and N95. A proper mask must be used to protect oneself and others from the spread of the coronavirus. This paper proposes CoViMask, a face mask type detector that detects the type of mask that a person is wearing, and is trained using a custom-made dataset. Accuracy, precision and recall are used to evaluate the proposed method. The paper also mentions the application areas. The results obtained prove that CoViMask is efficient in mask type detection and may aid in controlling the spread of covid.
{"title":"CoViMask: A Novel Face Mask Type Detector Using Convolutional Neural Networks","authors":"Sahana Rangasrinivasan, Sri Lohitha Bhagam, Nair K. Athira, Kondapi Niharika, Anjuna D. Raj, T. Anjali","doi":"10.1109/wispnet54241.2022.9767107","DOIUrl":"https://doi.org/10.1109/wispnet54241.2022.9767107","url":null,"abstract":"The COVID-19 pandemic has led to many lifestyle changes, one of them being the mandatory use of face masks in public settings. Given the importance of masks, there are various types for people to use, such as cloth and N95. A proper mask must be used to protect oneself and others from the spread of the coronavirus. This paper proposes CoViMask, a face mask type detector that detects the type of mask that a person is wearing, and is trained using a custom-made dataset. Accuracy, precision and recall are used to evaluate the proposed method. The paper also mentions the application areas. The results obtained prove that CoViMask is efficient in mask type detection and may aid in controlling the spread of covid.","PeriodicalId":432794,"journal":{"name":"2022 International Conference on Wireless Communications Signal Processing and Networking (WiSPNET)","volume":"74 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133612632","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：