Pub Date : 1900-01-01DOI: 10.26634/jcom.10.2.19059
Suputri Devi D. Anjani, E. Suneetha
Facial Expression Recognition (FER) has grown in popularity as a result of the recent advancement and use of humancomputer interface technologies. Because the images can vary in brightness, backdrop, position, etc. it is challenging for current machine learning and deep learning models to identify facial expression. If the database is small, it doesn't operate well. Feature extraction is crucial for FER, and if the derived characteristics can be separated, even a straightforward approach can help tremendously. Deep learning techniques and automated feature extraction, allow some irrelevant features to conflict with important features. In this paper, we deal with limited data and simply extract useful features from images. To make data more numerous and allow for the extraction of just important facial features, we suggest innovative face cropping, rotation, and simplification procedures and advocate using the Transfer Learning technique to construct DCNN for building a very accurate FER system. By replacing the dense top layer(s) with FER, a pretrained DCNN model is adopted, and the model is then modified with facial expression data. The training of the dense layer(s) is followed by adjusting each of the pre-trained DCNN blocks in turn. This new pipeline technique has gradually increased the accuracy of FER to a higher degree. On the CK+ and JAFFE datasets, experiments were run to assess the suggested methodology. For 7-class studies on the CK+ and JAFFE databases, high average accuracy in recognition of 99.49% and 98.58% were acquired.
{"title":"Transfer learning based effective emotional face recognition using DCNN via cropping techniques","authors":"Suputri Devi D. Anjani, E. Suneetha","doi":"10.26634/jcom.10.2.19059","DOIUrl":"https://doi.org/10.26634/jcom.10.2.19059","url":null,"abstract":"Facial Expression Recognition (FER) has grown in popularity as a result of the recent advancement and use of humancomputer interface technologies. Because the images can vary in brightness, backdrop, position, etc. it is challenging for current machine learning and deep learning models to identify facial expression. If the database is small, it doesn't operate well. Feature extraction is crucial for FER, and if the derived characteristics can be separated, even a straightforward approach can help tremendously. Deep learning techniques and automated feature extraction, allow some irrelevant features to conflict with important features. In this paper, we deal with limited data and simply extract useful features from images. To make data more numerous and allow for the extraction of just important facial features, we suggest innovative face cropping, rotation, and simplification procedures and advocate using the Transfer Learning technique to construct DCNN for building a very accurate FER system. By replacing the dense top layer(s) with FER, a pretrained DCNN model is adopted, and the model is then modified with facial expression data. The training of the dense layer(s) is followed by adjusting each of the pre-trained DCNN blocks in turn. This new pipeline technique has gradually increased the accuracy of FER to a higher degree. On the CK+ and JAFFE datasets, experiments were run to assess the suggested methodology. For 7-class studies on the CK+ and JAFFE databases, high average accuracy in recognition of 99.49% and 98.58% were acquired.","PeriodicalId":130578,"journal":{"name":"i-manager's Journal on Computer Science","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125975260","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}
S. Anishkumar, Padmapadanand Bhaskara, S. Shanthi, P. Charukesh
{"title":"AUTOMATED TRAFFIC NAVIGATION SYSTEM USING DEEP\u0000LEARNING","authors":"S. Anishkumar, Padmapadanand Bhaskara, S. Shanthi, P. Charukesh","doi":"10.26634/jcom.9.1.18112","DOIUrl":"https://doi.org/10.26634/jcom.9.1.18112","url":null,"abstract":"","PeriodicalId":130578,"journal":{"name":"i-manager's Journal on Computer Science","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128114725","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}
J. Samatha, Prashanth Reddy Voladri, S. Dhanunjay, Sai Koundinya Gattu
{"title":"VERIFICATION FOR ONLINE SIGNATURE BIOMETRICS USING DEEP\u0000LEARNING","authors":"J. Samatha, Prashanth Reddy Voladri, S. Dhanunjay, Sai Koundinya Gattu","doi":"10.26634/jcom.8.3.18074","DOIUrl":"https://doi.org/10.26634/jcom.8.3.18074","url":null,"abstract":"","PeriodicalId":130578,"journal":{"name":"i-manager's Journal on Computer Science","volume":"63 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127247380","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}
Shoaib Muhammad, Muhammad Nabeel Mustafa Syed, Shabhi Ul Hasan Naqvi Syed
Cloud computing is the on-demand availability of computer system resources. Most technology industries are moving to the cloud. Cloud structures can be costly for users. Virtualization is used in cloud computing that helps the cloud at a low cost. Migrating virtual machines (VMs) helps to manage computation. Migration of virtual machines is a core feature of virtualization. The technique of migrating a running virtual machine from one physical host to another with minimal downtime is called "live virtual machine migration." This paper discusses the migration technique, i.e., migration before and after copying, and also issues related to live migration. This paper presents a better approach to the VM migration method and future challenges by differentiating from the previous live VM migration method.
{"title":"Techniques of migration in live virtual machine and its challenges","authors":"Shoaib Muhammad, Muhammad Nabeel Mustafa Syed, Shabhi Ul Hasan Naqvi Syed","doi":"10.26634/jcom.9.4.18540","DOIUrl":"https://doi.org/10.26634/jcom.9.4.18540","url":null,"abstract":"Cloud computing is the on-demand availability of computer system resources. Most technology industries are moving to the cloud. Cloud structures can be costly for users. Virtualization is used in cloud computing that helps the cloud at a low cost. Migrating virtual machines (VMs) helps to manage computation. Migration of virtual machines is a core feature of virtualization. The technique of migrating a running virtual machine from one physical host to another with minimal downtime is called \"live virtual machine migration.\" This paper discusses the migration technique, i.e., migration before and after copying, and also issues related to live migration. This paper presents a better approach to the VM migration method and future challenges by differentiating from the previous live VM migration method.","PeriodicalId":130578,"journal":{"name":"i-manager's Journal on Computer Science","volume":"2016 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127265735","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"E-SHOPPING WEBSITE PERFORMANCE ANALYSIS AND PREDICTION\u0000REVIEW USING SENTIMENT ANALYSIS","authors":"Shiny S. Jeba","doi":"10.26634/jcom.9.2.18430","DOIUrl":"https://doi.org/10.26634/jcom.9.2.18430","url":null,"abstract":"","PeriodicalId":130578,"journal":{"name":"i-manager's Journal on Computer Science","volume":"135 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127349958","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"DEEP LEARNING TECHNIQUES TO ADDRESS CHALLENGES\u0000IN BIG DATA","authors":"C. Pabitha, B. Vanathi","doi":"10.26634/jcom.9.3.16794","DOIUrl":"https://doi.org/10.26634/jcom.9.3.16794","url":null,"abstract":"","PeriodicalId":130578,"journal":{"name":"i-manager's Journal on Computer Science","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128866964","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"ARPIT: AMBIGUITY RESOLVER FOR POS TAGGING OF TELUGU, AN INDIAN LANGUAGE","authors":"E. Suneetha, L. Sumalatha","doi":"10.26634/jcom.7.1.15372","DOIUrl":"https://doi.org/10.26634/jcom.7.1.15372","url":null,"abstract":"","PeriodicalId":130578,"journal":{"name":"i-manager's Journal on Computer Science","volume":"45 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132217474","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 : 1900-01-01DOI: 10.26634/jcom.10.1.18752
Kumar Soni Vijay, Selot Smita
In the domain of natural language processing, sentiment analysis is an important field for any review. Nowadays Indian languages are more popular for any product review. In North India, Hindi is the most widely used language. People having Hindi as their mother tongue can easily express their opinions and thoughts through that language. In the field of research, Hindi language has many challenges due to very less research work, limited data for analysis and less size of corpus data. Deep learning techniques are currently used for predicting feelings. Recurrent Neural Network (RNN), particularly the Long Short Term Memory (LSTM) and Convolution Neural Network (CNN), are two generally used deep learning approaches. Depending on the domain area of application, the strategies are utilized in combinations or as stand-alone procedures. This review paper emphases on the numerous flavours of deep learning approaches employed in various applications of sentiment analysis at the sentence and aspect levels.
{"title":"A survey of deep learning techniques in the field of sentiment analysis for the hindi language","authors":"Kumar Soni Vijay, Selot Smita","doi":"10.26634/jcom.10.1.18752","DOIUrl":"https://doi.org/10.26634/jcom.10.1.18752","url":null,"abstract":"In the domain of natural language processing, sentiment analysis is an important field for any review. Nowadays Indian languages are more popular for any product review. In North India, Hindi is the most widely used language. People having Hindi as their mother tongue can easily express their opinions and thoughts through that language. In the field of research, Hindi language has many challenges due to very less research work, limited data for analysis and less size of corpus data. Deep learning techniques are currently used for predicting feelings. Recurrent Neural Network (RNN), particularly the Long Short Term Memory (LSTM) and Convolution Neural Network (CNN), are two generally used deep learning approaches. Depending on the domain area of application, the strategies are utilized in combinations or as stand-alone procedures. This review paper emphases on the numerous flavours of deep learning approaches employed in various applications of sentiment analysis at the sentence and aspect levels.","PeriodicalId":130578,"journal":{"name":"i-manager's Journal on Computer Science","volume":"51 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132703302","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：