Pub Date : 2020-12-04DOI: 10.1109/IBSSC51096.2020.9332167
Sudeep D. Thepade, Divesh M. Bakshani, Tanvi Bhingurde, Shivaji Burghate, Shreepad Deshmankar
Image Splicing is known as a conventional type of digital image manipulation. It is one such type of tampering; also called as image composition. A spliced (or composite) image is usually created by copying and pasting portions of the image onto the same or another image. Spliced image detection mainly deals with finding similarity present in an image and establishing a relationship between authentic image parts and pasted portions of the image. With the increasing popularity and usage of easily available image editing technologies, even for people with minimal expertise it has become much easier to edit image data. Hence splicing is becoming sophisticated day by day making it difficult to detect with naked eyes. Due to the advent of social media and other platforms these spliced images can be circulated in faster ways among users of those platforms and hence it becomes necessary to come up with methods of spliced image detection. This paper proposes use of Thepade’s Sorted BTC, various Machine Learning classifiers for splicing detection. Here TSTBTC-Nary is explored with values of n as 2, 4, 6,…16,18 attempted on some machine learning classifiers (BayesNet, NaiveBayes, Logistic, Simple Logistic, SVM, JRip, PART, J48, LMT) for various performance metrics. After validation on 3 benchmark datasets CASIA V1, Columbia and Columbia-Uncompressed, LMT classifier performs better closely followed by Simple Logistic and J48. Better image splicing capabilities are observed with TSTBTC 16-ary closely followed by 18-ary and 14-ary.
{"title":"Performance Appraise of Machine Learning Classifiers in Image Splicing Detection using Thepade’s Sorted Block Truncation Coding","authors":"Sudeep D. Thepade, Divesh M. Bakshani, Tanvi Bhingurde, Shivaji Burghate, Shreepad Deshmankar","doi":"10.1109/IBSSC51096.2020.9332167","DOIUrl":"https://doi.org/10.1109/IBSSC51096.2020.9332167","url":null,"abstract":"Image Splicing is known as a conventional type of digital image manipulation. It is one such type of tampering; also called as image composition. A spliced (or composite) image is usually created by copying and pasting portions of the image onto the same or another image. Spliced image detection mainly deals with finding similarity present in an image and establishing a relationship between authentic image parts and pasted portions of the image. With the increasing popularity and usage of easily available image editing technologies, even for people with minimal expertise it has become much easier to edit image data. Hence splicing is becoming sophisticated day by day making it difficult to detect with naked eyes. Due to the advent of social media and other platforms these spliced images can be circulated in faster ways among users of those platforms and hence it becomes necessary to come up with methods of spliced image detection. This paper proposes use of Thepade’s Sorted BTC, various Machine Learning classifiers for splicing detection. Here TSTBTC-Nary is explored with values of n as 2, 4, 6,…16,18 attempted on some machine learning classifiers (BayesNet, NaiveBayes, Logistic, Simple Logistic, SVM, JRip, PART, J48, LMT) for various performance metrics. After validation on 3 benchmark datasets CASIA V1, Columbia and Columbia-Uncompressed, LMT classifier performs better closely followed by Simple Logistic and J48. Better image splicing capabilities are observed with TSTBTC 16-ary closely followed by 18-ary and 14-ary.","PeriodicalId":432093,"journal":{"name":"2020 IEEE Bombay Section Signature Conference (IBSSC)","volume":"46 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121315822","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 : 2020-12-04DOI: 10.1109/IBSSC51096.2020.9332219
Sudeep D. Thepade, Divesh M. Bakshani, Tanvi Bhingurde, Shivaji Burghate, Shreepad Deshmankar
The era of digitization has accelerated communication and information sharing immensely. With ever-growing digital advancements in technology and applications cybersecurity poses to be a pressing issue. The amount of growth in data exchange is exponential thus making automated processes a vital tool to deliver security. Image editing technologies manipulate image data and have enabled all types of users to tamper images resulting in widespread fake images. Distorted information carries heavy consequences and thus a reliable image forgery detection system is essential. This paper proposes a machine learning-based approach for image splicing detection using the global and local characteristics of the image. TSBTC N-ary, with the value of N = 12,14 and 16, is applied along with LBP for feature extraction and various Machine learning classifiers are implemented and compared for image splicing detection. The performance of the proposed method is tested and validated on 3 benchmark datasets: CASIA V1 Dataset, Columbia Dataset, and Columbia Uncompressed Dataset. Results are evaluated based on various performance metrics.
{"title":"Thepade’s Sorted Block Truncation Coding Applied on Local Binary Patterns of Images for Splicing Identification Using Machine Learning Classifiers","authors":"Sudeep D. Thepade, Divesh M. Bakshani, Tanvi Bhingurde, Shivaji Burghate, Shreepad Deshmankar","doi":"10.1109/IBSSC51096.2020.9332219","DOIUrl":"https://doi.org/10.1109/IBSSC51096.2020.9332219","url":null,"abstract":"The era of digitization has accelerated communication and information sharing immensely. With ever-growing digital advancements in technology and applications cybersecurity poses to be a pressing issue. The amount of growth in data exchange is exponential thus making automated processes a vital tool to deliver security. Image editing technologies manipulate image data and have enabled all types of users to tamper images resulting in widespread fake images. Distorted information carries heavy consequences and thus a reliable image forgery detection system is essential. This paper proposes a machine learning-based approach for image splicing detection using the global and local characteristics of the image. TSBTC N-ary, with the value of N = 12,14 and 16, is applied along with LBP for feature extraction and various Machine learning classifiers are implemented and compared for image splicing detection. The performance of the proposed method is tested and validated on 3 benchmark datasets: CASIA V1 Dataset, Columbia Dataset, and Columbia Uncompressed Dataset. Results are evaluated based on various performance metrics.","PeriodicalId":432093,"journal":{"name":"2020 IEEE Bombay Section Signature Conference (IBSSC)","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117282768","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 : 2020-12-04DOI: 10.1109/IBSSC51096.2020.9332171
Sanjib Deka, Subhasish Goswami, A. Anand
Maintenance of immutable vaccination records and provision of accessing the records in order to prove immunity has been the need of the hour. The recent spread of Covid19 and related uncertainty over vaccinations and immunity have made the search for a secure trustable system for reporting vaccination data more essential. Multiple digital, as well as paper-based solutions have been tested but none has been reported successful enough. In this paper, a technique has been proposed to solve the problem by introducing blockchain-based solution to maintain records of vaccination and proof of immunity for individuals. The purpose has been to present a safe and efficient solution to the problem and hence the model proposed is based on concepts of smart contracts and built over Ethereum blockchain. The paper goes on to give a detailed study of the technique based on discussions of its various aspects like design, development and feasibility.
{"title":"A Blockchain Based Technique for Storing Vaccination Records","authors":"Sanjib Deka, Subhasish Goswami, A. Anand","doi":"10.1109/IBSSC51096.2020.9332171","DOIUrl":"https://doi.org/10.1109/IBSSC51096.2020.9332171","url":null,"abstract":"Maintenance of immutable vaccination records and provision of accessing the records in order to prove immunity has been the need of the hour. The recent spread of Covid19 and related uncertainty over vaccinations and immunity have made the search for a secure trustable system for reporting vaccination data more essential. Multiple digital, as well as paper-based solutions have been tested but none has been reported successful enough. In this paper, a technique has been proposed to solve the problem by introducing blockchain-based solution to maintain records of vaccination and proof of immunity for individuals. The purpose has been to present a safe and efficient solution to the problem and hence the model proposed is based on concepts of smart contracts and built over Ethereum blockchain. The paper goes on to give a detailed study of the technique based on discussions of its various aspects like design, development and feasibility.","PeriodicalId":432093,"journal":{"name":"2020 IEEE Bombay Section Signature Conference (IBSSC)","volume":"122 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130553273","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 : 2020-12-04DOI: 10.1109/IBSSC51096.2020.9332180
P. M. Pardhi, Sudeep D. Thepade
The usage of digital images is growing because of the benefits possessed by digital images in many ways in day to day life. But not all the images captured have a filmic appearance that pleases the human eye. Dissatisfaction is mainly because of noise addition, bad illumination where the captured image is either extra dark or bright, which leads to the need of enhancement in the quality of images. The motivation behind enhancement of image is to grasp the hidden information which is unavailable during image acquisition due to improper light conditions. One way to do so is enhancing the contrast of poorly illuminated images. In this paper, a new technique is presented which fuses HE enhanced image with proposed algorithm using wavelet transform. The results are tested on 240 images of 12 different categories ExDark dataset. Performance measures used are Entropy, NIQE and BRISQUE.
{"title":"Enhancement of Nighttime Image Visibility Using Wavelet Fusion of Equalized Color Channels and Luminance with Kekre’s LUV Color Space","authors":"P. M. Pardhi, Sudeep D. Thepade","doi":"10.1109/IBSSC51096.2020.9332180","DOIUrl":"https://doi.org/10.1109/IBSSC51096.2020.9332180","url":null,"abstract":"The usage of digital images is growing because of the benefits possessed by digital images in many ways in day to day life. But not all the images captured have a filmic appearance that pleases the human eye. Dissatisfaction is mainly because of noise addition, bad illumination where the captured image is either extra dark or bright, which leads to the need of enhancement in the quality of images. The motivation behind enhancement of image is to grasp the hidden information which is unavailable during image acquisition due to improper light conditions. One way to do so is enhancing the contrast of poorly illuminated images. In this paper, a new technique is presented which fuses HE enhanced image with proposed algorithm using wavelet transform. The results are tested on 240 images of 12 different categories ExDark dataset. Performance measures used are Entropy, NIQE and BRISQUE.","PeriodicalId":432093,"journal":{"name":"2020 IEEE Bombay Section Signature Conference (IBSSC)","volume":"157 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114327567","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 : 2020-12-04DOI: 10.1109/IBSSC51096.2020.9332163
Gauri V. Nair, Y. Jeppu, M. Tahiliani
The COVID-19 pandemic is rampant in India and this has changed the way the students and teachers interact with each other during a course. An added complexity is the introduction of the Industry Academia participation in terms of Adjunct Faculties. Teaching formal methods to undergraduate students has been difficult and these are well captured in the academic community. The necessity of good requirements writing which can be validated using formal methods is a need of the hour for the industry. Requirements error contribute to 70% of the errors in safety critical projects. A course on Formal Methods is offered at the National Institute of Technology Karnataka, Surathkal as an undergraduate elective. This has 54 students registered and the course is offered online by an adjunct faculty from the industry. The experiences of capturing and writing good requirements using the EARS (Easy Approach to Requirements Syntax) is highlighted in this paper. A survey of before and after the class and an exercise on EARS notations are brought out. The lessons learnt and the efficacy of the teaching is brought out as a three perspective: student, academia and industry.
{"title":"Teaching EARS to Undergrads in the Pandemic - Industry Academia Experience","authors":"Gauri V. Nair, Y. Jeppu, M. Tahiliani","doi":"10.1109/IBSSC51096.2020.9332163","DOIUrl":"https://doi.org/10.1109/IBSSC51096.2020.9332163","url":null,"abstract":"The COVID-19 pandemic is rampant in India and this has changed the way the students and teachers interact with each other during a course. An added complexity is the introduction of the Industry Academia participation in terms of Adjunct Faculties. Teaching formal methods to undergraduate students has been difficult and these are well captured in the academic community. The necessity of good requirements writing which can be validated using formal methods is a need of the hour for the industry. Requirements error contribute to 70% of the errors in safety critical projects. A course on Formal Methods is offered at the National Institute of Technology Karnataka, Surathkal as an undergraduate elective. This has 54 students registered and the course is offered online by an adjunct faculty from the industry. The experiences of capturing and writing good requirements using the EARS (Easy Approach to Requirements Syntax) is highlighted in this paper. A survey of before and after the class and an exercise on EARS notations are brought out. The lessons learnt and the efficacy of the teaching is brought out as a three perspective: student, academia and industry.","PeriodicalId":432093,"journal":{"name":"2020 IEEE Bombay Section Signature Conference (IBSSC)","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124686691","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}
The marketing is carried out by using various social media strategies and platforms like Facebook, Instagram, Twitter, Pinterest, LinkedIn, YouTube, etc. these are various platforms that are used for marketing. The audience satisfaction delivers many benefits like loyalty, an increase of being referral, less likely to churn, repeat purchase, buying the product at a premium price. The objective of this project is to analyze customer comments in order to extract product details, issue type, sentiments/emotion using topic modeling which will also showcase keywords fall under particular topics to improve customer satisfaction scores. The customer journey can be analyzed to understand the needs and requirements of customer which when post purchasable of the product also help in understanding customer fulfilment ratio. This project not only helps to understand that promotion through social media is better than the traditional approach but also helps to understand the adaptation of new social media x strategies and their promotion along with customer satisfaction.
{"title":"Optimization Of Social Media Comments To Improve Customer Journey Using Machine Learning","authors":"Tejas Sanjay Chougule, Swati Nadkarni, Bhavesh Patel","doi":"10.1109/IBSSC51096.2020.9332188","DOIUrl":"https://doi.org/10.1109/IBSSC51096.2020.9332188","url":null,"abstract":"The marketing is carried out by using various social media strategies and platforms like Facebook, Instagram, Twitter, Pinterest, LinkedIn, YouTube, etc. these are various platforms that are used for marketing. The audience satisfaction delivers many benefits like loyalty, an increase of being referral, less likely to churn, repeat purchase, buying the product at a premium price. The objective of this project is to analyze customer comments in order to extract product details, issue type, sentiments/emotion using topic modeling which will also showcase keywords fall under particular topics to improve customer satisfaction scores. The customer journey can be analyzed to understand the needs and requirements of customer which when post purchasable of the product also help in understanding customer fulfilment ratio. This project not only helps to understand that promotion through social media is better than the traditional approach but also helps to understand the adaptation of new social media x strategies and their promotion along with customer satisfaction.","PeriodicalId":432093,"journal":{"name":"2020 IEEE Bombay Section Signature Conference (IBSSC)","volume":"114 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126905329","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 : 2020-12-04DOI: 10.1109/IBSSC51096.2020.9332221
Ahona Ghosh, S. Saha
With the quick increase in world-wide population, need of automation is getting increased in every field. Employability tests are often used to check the ability of an experienced or fresher employee to work in a team and also their skill, to know how their actions can impact others. In this context, automated employability test for factory workers will motivate people to stay employable in the labor force of the future and help the organizations to perform recruitment process in an efficient manner. In this paper, we have proposed an automatic employability test platform using Collaborative filtering where similar and best matched activities have been recognized first by the use of item-based-collaborative filtering and then based on the performance of similar activities done by similar subjects, the ranking of employability has been determined for unknown workers using User-basedcollaborative filtering. If the ranking is higher than a previously defined threshold, the subject is said to be appropriate in the scenario and his/her employability is confirmed, but if the ranking is less than the threshold, then the subject is asked to practice more and take the next assessment of employability. To deal with the difference in body structure and habits of doing same action differently at first, we have considered the mean of the rankings of seven different activities and then weighted rank has been calculated to take the inter personal similarity into account. The proposed system is a novel work in this domain and outperforms the other existing works also.
{"title":"Automatic Employability Test for Factory Workers using Collaborative Filtering","authors":"Ahona Ghosh, S. Saha","doi":"10.1109/IBSSC51096.2020.9332221","DOIUrl":"https://doi.org/10.1109/IBSSC51096.2020.9332221","url":null,"abstract":"With the quick increase in world-wide population, need of automation is getting increased in every field. Employability tests are often used to check the ability of an experienced or fresher employee to work in a team and also their skill, to know how their actions can impact others. In this context, automated employability test for factory workers will motivate people to stay employable in the labor force of the future and help the organizations to perform recruitment process in an efficient manner. In this paper, we have proposed an automatic employability test platform using Collaborative filtering where similar and best matched activities have been recognized first by the use of item-based-collaborative filtering and then based on the performance of similar activities done by similar subjects, the ranking of employability has been determined for unknown workers using User-basedcollaborative filtering. If the ranking is higher than a previously defined threshold, the subject is said to be appropriate in the scenario and his/her employability is confirmed, but if the ranking is less than the threshold, then the subject is asked to practice more and take the next assessment of employability. To deal with the difference in body structure and habits of doing same action differently at first, we have considered the mean of the rankings of seven different activities and then weighted rank has been calculated to take the inter personal similarity into account. The proposed system is a novel work in this domain and outperforms the other existing works also.","PeriodicalId":432093,"journal":{"name":"2020 IEEE Bombay Section Signature Conference (IBSSC)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130933660","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 : 2020-12-04DOI: 10.1109/IBSSC51096.2020.9332211
Abhijit Poddar, Monali Poddar
A smartphone or a tablet running on Android has been used to control an experiment to determine the energy band gap of a semiconductor. The smartphone is interfaced with the experimental circuit through a cheap microcontroller. A dedicated android application has been developed to help the user perform the experiment by acquisition and plotting of the data in real time. Curve-fitting and novel graphical techniques have been employed to determine the energy band gap, bypassing the need to use expensive electronic instruments. The graphs may be plotted on a virtual e-graph paper mimicking an actual graph paper on the smartphone screen. Since the user may not touch any instrument except his own smartphone while carrying out the experiment, chances of acquiring Covid-19 inside the laboratory would also have been reduced.
{"title":"A Smartphone Controlled Experiment to determine the Energy Band Gap of a Semiconductor using Novel Graphical Techniques","authors":"Abhijit Poddar, Monali Poddar","doi":"10.1109/IBSSC51096.2020.9332211","DOIUrl":"https://doi.org/10.1109/IBSSC51096.2020.9332211","url":null,"abstract":"A smartphone or a tablet running on Android has been used to control an experiment to determine the energy band gap of a semiconductor. The smartphone is interfaced with the experimental circuit through a cheap microcontroller. A dedicated android application has been developed to help the user perform the experiment by acquisition and plotting of the data in real time. Curve-fitting and novel graphical techniques have been employed to determine the energy band gap, bypassing the need to use expensive electronic instruments. The graphs may be plotted on a virtual e-graph paper mimicking an actual graph paper on the smartphone screen. Since the user may not touch any instrument except his own smartphone while carrying out the experiment, chances of acquiring Covid-19 inside the laboratory would also have been reduced.","PeriodicalId":432093,"journal":{"name":"2020 IEEE Bombay Section Signature Conference (IBSSC)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129999545","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}
This paper presents how blockchain can be leveraged in the domain of trade finance, to provide an adept model, which simplifies the end-to-end process. The paper elaborates upon the integration of the components of trade finance with blockchain. We discuss the traditional trade finance model and how the integrated blockchain model helps mitigate its pain points. Using this integrated model, a trade transaction that would normally take close to a week can be successfully executed in, approximately, a quarter of a day. The process flow of the events of a transaction powered by blockchain are elucidated upon. This paper highlights how distributed ledgers, smart contracts, events, and system integration will power trade finance. The key features which are focused on include - authentication, decentralization, immutability, and consensus mechanisms. Furthermore, we explore the benefits and functionalities of adopting blockchain, which includes - efficiency, transparency, collaboration, and auditability and the way they can be achieved without compromising security, confidentiality, and interoperability. The objective of the paper is to illustrate how blockchain technology can reshape the landscape of Trade Finance and improve financial mechanisms.
{"title":"An Intrinsic Review on Trade Finance Using Blockchain","authors":"Neelika Chakrabarti, Vibhor Gupta, Shilpika Agarwal","doi":"10.1109/IBSSC51096.2020.9332181","DOIUrl":"https://doi.org/10.1109/IBSSC51096.2020.9332181","url":null,"abstract":"This paper presents how blockchain can be leveraged in the domain of trade finance, to provide an adept model, which simplifies the end-to-end process. The paper elaborates upon the integration of the components of trade finance with blockchain. We discuss the traditional trade finance model and how the integrated blockchain model helps mitigate its pain points. Using this integrated model, a trade transaction that would normally take close to a week can be successfully executed in, approximately, a quarter of a day. The process flow of the events of a transaction powered by blockchain are elucidated upon. This paper highlights how distributed ledgers, smart contracts, events, and system integration will power trade finance. The key features which are focused on include - authentication, decentralization, immutability, and consensus mechanisms. Furthermore, we explore the benefits and functionalities of adopting blockchain, which includes - efficiency, transparency, collaboration, and auditability and the way they can be achieved without compromising security, confidentiality, and interoperability. The objective of the paper is to illustrate how blockchain technology can reshape the landscape of Trade Finance and improve financial mechanisms.","PeriodicalId":432093,"journal":{"name":"2020 IEEE Bombay Section Signature Conference (IBSSC)","volume":"273 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121444690","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 : 2020-12-04DOI: 10.1109/IBSSC51096.2020.9332162
Jeevamol Joy, Renumol V G
Recommender systems in the e-learning domain assist learners in finding relevant learning materials based on their preferences and goals. One of the main components of such a recommender system is a similarity measurement unit, used to determine the set of learners having the same behavior. Several similarity functions have been proposed in the e-learning domain, with different performances in terms of accuracy and quality of recommendations. Most of these similarity methods do not perform satisfactorily in the presence of cold-start users. In this paper, we present a comparative study of 4 generic similarity measures (Pearson Correlation Similarity, Cosine Vector Similarity, Euclidean Distance Similarity, Jaccard Similarity Correlation) that are widely used in e-learning recommender systems. The evaluation metrics Mean Absolute Error (MAE) and Root Mean Square Error (RMSE) are used to evaluate the performance of the recommender system with the 4 similarity measures. The results indicate better recommendation performance when using Cosine Vector Similarity in cold-start condition.
{"title":"Comparison of Generic Similarity Measures in E-learning Content Recommender System in Cold-Start Condition","authors":"Jeevamol Joy, Renumol V G","doi":"10.1109/IBSSC51096.2020.9332162","DOIUrl":"https://doi.org/10.1109/IBSSC51096.2020.9332162","url":null,"abstract":"Recommender systems in the e-learning domain assist learners in finding relevant learning materials based on their preferences and goals. One of the main components of such a recommender system is a similarity measurement unit, used to determine the set of learners having the same behavior. Several similarity functions have been proposed in the e-learning domain, with different performances in terms of accuracy and quality of recommendations. Most of these similarity methods do not perform satisfactorily in the presence of cold-start users. In this paper, we present a comparative study of 4 generic similarity measures (Pearson Correlation Similarity, Cosine Vector Similarity, Euclidean Distance Similarity, Jaccard Similarity Correlation) that are widely used in e-learning recommender systems. The evaluation metrics Mean Absolute Error (MAE) and Root Mean Square Error (RMSE) are used to evaluate the performance of the recommender system with the 4 similarity measures. The results indicate better recommendation performance when using Cosine Vector Similarity in cold-start condition.","PeriodicalId":432093,"journal":{"name":"2020 IEEE Bombay Section Signature Conference (IBSSC)","volume":"63 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114814894","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：