Pub Date : 2023-06-29DOI: 10.1109/SCSE59836.2023.10215007
M. Gunathilaka, C. Kavirathna, A. Wijayanayake, Jinadari Prabodhika
Companies constantly adapt their global business procedures to increase overall performance in today’s business environment. To focus on core business processes, many manufacturing and retailing organizations are outsourcing logistic services to 3PL companies. Warehousing is one of the most outsourced services from logistic services. In this environment, warehouse operations play a key and critical role in achieving good performance through numerous upgrades. Warehouse performance measures are taken now as a technique of measuring activity performance, programs, or services supplied by a warehouse. Although the Sri Lankan 3PL industry has poor logistic performance compared to the global 3PL industry, Sri Lanka has the geographic advantage required to develop into an important logistical hub in South Asia because it is located close to India and on the East-West trade route. Therefore, this research investigates the Warehouse performance measures through a literature review and validated those for the Sri Lankan third-party logistic warehouses through industry experts’ opinions. Identified warehouse performance measures were prioritized using the Analytical Hierarchy Process (AHP) as a weighting method to focus on major categories and major warehouse performance measures. Because numerous criteria and indicators must be considered for measuring warehouse performance, a Composite Warehouse Performance Index (CWPI) is built utilizing the Analytical Hierarchy Process (AHP) as a linear aggregation approach. The proposed model was tested with a customer who receives warehousing services from three third-party logistic organizations.
{"title":"Prioritizing Warehouse Performance Measures in Sri Lankan 3PL Industry","authors":"M. Gunathilaka, C. Kavirathna, A. Wijayanayake, Jinadari Prabodhika","doi":"10.1109/SCSE59836.2023.10215007","DOIUrl":"https://doi.org/10.1109/SCSE59836.2023.10215007","url":null,"abstract":"Companies constantly adapt their global business procedures to increase overall performance in today’s business environment. To focus on core business processes, many manufacturing and retailing organizations are outsourcing logistic services to 3PL companies. Warehousing is one of the most outsourced services from logistic services. In this environment, warehouse operations play a key and critical role in achieving good performance through numerous upgrades. Warehouse performance measures are taken now as a technique of measuring activity performance, programs, or services supplied by a warehouse. Although the Sri Lankan 3PL industry has poor logistic performance compared to the global 3PL industry, Sri Lanka has the geographic advantage required to develop into an important logistical hub in South Asia because it is located close to India and on the East-West trade route. Therefore, this research investigates the Warehouse performance measures through a literature review and validated those for the Sri Lankan third-party logistic warehouses through industry experts’ opinions. Identified warehouse performance measures were prioritized using the Analytical Hierarchy Process (AHP) as a weighting method to focus on major categories and major warehouse performance measures. Because numerous criteria and indicators must be considered for measuring warehouse performance, a Composite Warehouse Performance Index (CWPI) is built utilizing the Analytical Hierarchy Process (AHP) as a linear aggregation approach. The proposed model was tested with a customer who receives warehousing services from three third-party logistic organizations.","PeriodicalId":429228,"journal":{"name":"2023 International Research Conference on Smart Computing and Systems Engineering (SCSE)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126300136","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 : 2023-06-29DOI: 10.1109/SCSE59836.2023.10215038
C. D. Fernando, C. Walgampaya
Online advertising has grown drastically over the last couple of decades by making billions worth of business markets all over the world. Click Fraud can be identified as one of the common malpractices when it comes to digital platforms. This leads to an increase in the revenue of the Ad publishers and huge losses for the advertisers. Hence the need of detecting click fraud has become a major concern in online marketing. Recent studies have proposed different kinds of machine learning based approaches to detect these fraud activities. In this study, we propose an improved Lenet-5 Convolution Neural Network to identify click fraud. This proposed novel deep learning algorithm was able to achieve an accuracy of 99.09% by using deep features of the proposed Lenet-5 based Convolution Neural Network.
{"title":"Detecting Click Fraud Using an Improved Lenet-5 Convolution Neural Network","authors":"C. D. Fernando, C. Walgampaya","doi":"10.1109/SCSE59836.2023.10215038","DOIUrl":"https://doi.org/10.1109/SCSE59836.2023.10215038","url":null,"abstract":"Online advertising has grown drastically over the last couple of decades by making billions worth of business markets all over the world. Click Fraud can be identified as one of the common malpractices when it comes to digital platforms. This leads to an increase in the revenue of the Ad publishers and huge losses for the advertisers. Hence the need of detecting click fraud has become a major concern in online marketing. Recent studies have proposed different kinds of machine learning based approaches to detect these fraud activities. In this study, we propose an improved Lenet-5 Convolution Neural Network to identify click fraud. This proposed novel deep learning algorithm was able to achieve an accuracy of 99.09% by using deep features of the proposed Lenet-5 based Convolution Neural Network.","PeriodicalId":429228,"journal":{"name":"2023 International Research Conference on Smart Computing and Systems Engineering (SCSE)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130710693","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}
In today’s digital age, protecting sensitive data during transmission and storage is a critical concern. The rise of cyber threats has made it essential to develop secure communication channels to prevent unauthorized access and theft of confidential information. In this research, we propose a system that utilizes a combination of steganography and visual cryptography for secure data hiding. The main goal of this research is to address the issue of secure communication by concealing information in a digital image using steganography. After encoding the text in the image, the resulting steganographic image is divided into two shares using visual cryptography, ensuring that the data is protected from unauthorized access. This approach offers a practical and effective solution for secure data hiding, which can have potential applications in fields such as information security, privacy protection, and digital forensics. Overall, this research offers a viable solution to the problem of secure communication, which can help safeguard confidential information in today’s digital world.
{"title":"Web-Based Data Hiding: A Hybrid Approach Using Steganography and Visual Cryptography","authors":"Seniru Ediriweera, B.A.S. Dilhara, Chamara Disanayake","doi":"10.1109/SCSE59836.2023.10214994","DOIUrl":"https://doi.org/10.1109/SCSE59836.2023.10214994","url":null,"abstract":"In today’s digital age, protecting sensitive data during transmission and storage is a critical concern. The rise of cyber threats has made it essential to develop secure communication channels to prevent unauthorized access and theft of confidential information. In this research, we propose a system that utilizes a combination of steganography and visual cryptography for secure data hiding. The main goal of this research is to address the issue of secure communication by concealing information in a digital image using steganography. After encoding the text in the image, the resulting steganographic image is divided into two shares using visual cryptography, ensuring that the data is protected from unauthorized access. This approach offers a practical and effective solution for secure data hiding, which can have potential applications in fields such as information security, privacy protection, and digital forensics. Overall, this research offers a viable solution to the problem of secure communication, which can help safeguard confidential information in today’s digital world.","PeriodicalId":429228,"journal":{"name":"2023 International Research Conference on Smart Computing and Systems Engineering (SCSE)","volume":"228 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131804842","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 : 2023-06-29DOI: 10.1109/SCSE59836.2023.10215027
S. Adeeba, Kuhaneswaran Banujan, B. Kumara
Home Violence (HV) has been a persistent issue across the globe, transcending economic status and cultural boundaries. The COVID-19 pandemic has further exacerbated this problem, bringing it to the forefront of public discourse. This study aims to analyse the impact of HV by utilising Twitter data and Machine Learning (ML) techniques, categorising tweets into three groups: (i) HV Incident Tweets, (ii) HV Awareness Tweets, and (iii) HV Shelter Tweets. This categorisation provides several advantages, such as uncovering new or hidden evidence, filling information gaps, and identifying potential suspects. Over 40,000 tweets were collected using the Twitter API between April 2019 and July 2021. Data pre-processing and word embedding were performed to prepare the data for analysis. Initially, tweets were categorised into HV Positive (containing relevant information) and HV Negative (noise or unrelated content) groups. Manually labelled tweets were used for training and testing purposes. Machine learning models, including SVM, NB, Logistic Regression, Decision Tree (DT), Artificial Neural Networks (ANN), and LSTM, were employed for this task. Subsequently, HV Positive tweets were classified into the three aforementioned categories. Manually labelled tweets were again used for training and testing. Models such as Tf-IDF+SVM, Tf-IDF+DT, Tf-IDF+NB, and GloVe+LSTM were utilised. Several evaluation metrics were used to assess the performance of the models. The study’s results provide important new understandings of the prevalence, patterns, and causes of HV as they are reported on social media and how the general population reacts to these problems. The research clarifies how social media may help spread knowledge, provide assistance, and link victims to resources. These insights can be instrumental in informing policymakers, non-profit organisations, and researchers as they work to develop targeted interventions and strategies to address HV during and beyond the COVID-19 pandemic.
{"title":"The Role of Social Media (Twitter) in Analysing Home Violence: A Machine Learning Approach","authors":"S. Adeeba, Kuhaneswaran Banujan, B. Kumara","doi":"10.1109/SCSE59836.2023.10215027","DOIUrl":"https://doi.org/10.1109/SCSE59836.2023.10215027","url":null,"abstract":"Home Violence (HV) has been a persistent issue across the globe, transcending economic status and cultural boundaries. The COVID-19 pandemic has further exacerbated this problem, bringing it to the forefront of public discourse. This study aims to analyse the impact of HV by utilising Twitter data and Machine Learning (ML) techniques, categorising tweets into three groups: (i) HV Incident Tweets, (ii) HV Awareness Tweets, and (iii) HV Shelter Tweets. This categorisation provides several advantages, such as uncovering new or hidden evidence, filling information gaps, and identifying potential suspects. Over 40,000 tweets were collected using the Twitter API between April 2019 and July 2021. Data pre-processing and word embedding were performed to prepare the data for analysis. Initially, tweets were categorised into HV Positive (containing relevant information) and HV Negative (noise or unrelated content) groups. Manually labelled tweets were used for training and testing purposes. Machine learning models, including SVM, NB, Logistic Regression, Decision Tree (DT), Artificial Neural Networks (ANN), and LSTM, were employed for this task. Subsequently, HV Positive tweets were classified into the three aforementioned categories. Manually labelled tweets were again used for training and testing. Models such as Tf-IDF+SVM, Tf-IDF+DT, Tf-IDF+NB, and GloVe+LSTM were utilised. Several evaluation metrics were used to assess the performance of the models. The study’s results provide important new understandings of the prevalence, patterns, and causes of HV as they are reported on social media and how the general population reacts to these problems. The research clarifies how social media may help spread knowledge, provide assistance, and link victims to resources. These insights can be instrumental in informing policymakers, non-profit organisations, and researchers as they work to develop targeted interventions and strategies to address HV during and beyond the COVID-19 pandemic.","PeriodicalId":429228,"journal":{"name":"2023 International Research Conference on Smart Computing and Systems Engineering (SCSE)","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116504377","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 : 2023-06-29DOI: 10.1109/SCSE59836.2023.10215021
Chethima Dias, P. Wickramasinghe, Ashely Jayamalaki, Ramesh Sivaguru, Nilmini Rathnayake, P. Jayasinghe
Hybrid teaching become a major part of the teaching style for the higher education sector in the Sri Lankan context. Hybrid teaching allows for a part of the academics to go to the course physically and simultaneously permitted the rest to conduct the sessions applying videoconferencing from different locations. The objective of this research study is to explore the effectiveness of the hybrid teaching to enhance academics outcome in the business faculty of one of the leading private higher education institutes in Sri Lanka. The purpose of the study was to explore the effectiveness of hybrid teaching practices. The data for the study was collected through 11 semi-structured interviews and the data were analysed by using the content analysis. The results show that the effectiveness of the hybrid teaching is somewhat higher than traditional techniques from the perspective of the academics. In addition, based on the content analysis researchers have identified variables such as: perceptions of effectiveness, experience in different teaching capacities, instructor attitude and belief and challenges in hybrid teaching methods. The output of this study will be helped to recognize how academics perceive the effectiveness of hybrid teaching with these significant contents in one of the leading private higher education institutes.
{"title":"Effectiveness of Hybrid Teaching Methods: The Perspective of Academics (Special Reference to One of the Leading Private Higher Educational Institutes in Sri Lanka)","authors":"Chethima Dias, P. Wickramasinghe, Ashely Jayamalaki, Ramesh Sivaguru, Nilmini Rathnayake, P. Jayasinghe","doi":"10.1109/SCSE59836.2023.10215021","DOIUrl":"https://doi.org/10.1109/SCSE59836.2023.10215021","url":null,"abstract":"Hybrid teaching become a major part of the teaching style for the higher education sector in the Sri Lankan context. Hybrid teaching allows for a part of the academics to go to the course physically and simultaneously permitted the rest to conduct the sessions applying videoconferencing from different locations. The objective of this research study is to explore the effectiveness of the hybrid teaching to enhance academics outcome in the business faculty of one of the leading private higher education institutes in Sri Lanka. The purpose of the study was to explore the effectiveness of hybrid teaching practices. The data for the study was collected through 11 semi-structured interviews and the data were analysed by using the content analysis. The results show that the effectiveness of the hybrid teaching is somewhat higher than traditional techniques from the perspective of the academics. In addition, based on the content analysis researchers have identified variables such as: perceptions of effectiveness, experience in different teaching capacities, instructor attitude and belief and challenges in hybrid teaching methods. The output of this study will be helped to recognize how academics perceive the effectiveness of hybrid teaching with these significant contents in one of the leading private higher education institutes.","PeriodicalId":429228,"journal":{"name":"2023 International Research Conference on Smart Computing and Systems Engineering (SCSE)","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123522179","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 : 2023-06-29DOI: 10.1109/SCSE59836.2023.10215019
W.D.S Kasun Wijerathne, P. Peter
With technology playing an ever-increasingly significant part in our everyday lives, the study focused on profiling Gen Z Internet behavior and identifying factors influencing their online purchase intentions. Responses from 253 participants were captured using a standardized questionnaire in order to profile the online shopping behavior of Gen Z. The results showed that Gen Z heavily relies on the Internet for social media, education, and video streaming but spends less time on online purchasing. Significantly, there was a significant gender gap in their online shopping behavior, with females showing a higher propensity to shop online. Perceived enjoyment and perceived ease of use were the most significant factors influencing the online purchase intention of Gen Z. In contrast, subjective norm, perceived benefits, and perceived trust were less significant. The findings emphasize the importance of understanding the unique habits and preferences of this market segment and developing strategies to target them effectively.
{"title":"Profiling Gen Z: Influencing Online Purchase Intention","authors":"W.D.S Kasun Wijerathne, P. Peter","doi":"10.1109/SCSE59836.2023.10215019","DOIUrl":"https://doi.org/10.1109/SCSE59836.2023.10215019","url":null,"abstract":"With technology playing an ever-increasingly significant part in our everyday lives, the study focused on profiling Gen Z Internet behavior and identifying factors influencing their online purchase intentions. Responses from 253 participants were captured using a standardized questionnaire in order to profile the online shopping behavior of Gen Z. The results showed that Gen Z heavily relies on the Internet for social media, education, and video streaming but spends less time on online purchasing. Significantly, there was a significant gender gap in their online shopping behavior, with females showing a higher propensity to shop online. Perceived enjoyment and perceived ease of use were the most significant factors influencing the online purchase intention of Gen Z. In contrast, subjective norm, perceived benefits, and perceived trust were less significant. The findings emphasize the importance of understanding the unique habits and preferences of this market segment and developing strategies to target them effectively.","PeriodicalId":429228,"journal":{"name":"2023 International Research Conference on Smart Computing and Systems Engineering (SCSE)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127548779","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 : 2023-06-29DOI: 10.1109/scse59836.2023.10215006
{"title":"SCSE_2023 Conference Proceedings","authors":"","doi":"10.1109/scse59836.2023.10215006","DOIUrl":"https://doi.org/10.1109/scse59836.2023.10215006","url":null,"abstract":"","PeriodicalId":429228,"journal":{"name":"2023 International Research Conference on Smart Computing and Systems Engineering (SCSE)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125279213","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}
Work-life balance is a motivational factor that causes employees to work in the organization steadily in each situation. This study is aimed to examine the organizational characteristics that impact the work-life balance of teleworkers in the IT industry of Sri Lanka in the post-pandemic era. A thorough systematic literature review using the PRISMA framework was conducted to identify which characteristics influenced the work-life of teleworkers. Identified most appropriate characteristics were shortlisted by the industry expert. The conceptual framework was developed by using this past literature support, and then the actual characteristics were identified through the data analysis process. For this purpose, the questionnaires targeted employees who were working in the IT sector in Sri Lanka. samples (n = 149) were collected through online questionnaires and then collected samples were subjected to preliminary data analysis using the IBM SPSS tool to clean the data. Then PLS-SEM method was used to find the relationship between the variables. The study found that strategies are the most significant factor to determine a better work-life balance, though management support, technical support, and organizational culture have relationships between them but that are not significant factors to drive better work-life balance in the post-pandemic era. And the study concluded that if organizations need to more focus on strategies, especially job control, and decision-making strategies then they can maintain a better work-life balance for the IT sector employees in Sri Lanka after the pandemic period.
{"title":"Organizational Characteristics that Drive Better Worklife Balance in the Post-pandemic Teleworking Context: Evidence from the IT Sector in Sri Lanka","authors":"Sathurvanan Prabagaran, Janaka Wijayanayake, Shanaka Jayasinghe","doi":"10.1109/SCSE59836.2023.10215023","DOIUrl":"https://doi.org/10.1109/SCSE59836.2023.10215023","url":null,"abstract":"Work-life balance is a motivational factor that causes employees to work in the organization steadily in each situation. This study is aimed to examine the organizational characteristics that impact the work-life balance of teleworkers in the IT industry of Sri Lanka in the post-pandemic era. A thorough systematic literature review using the PRISMA framework was conducted to identify which characteristics influenced the work-life of teleworkers. Identified most appropriate characteristics were shortlisted by the industry expert. The conceptual framework was developed by using this past literature support, and then the actual characteristics were identified through the data analysis process. For this purpose, the questionnaires targeted employees who were working in the IT sector in Sri Lanka. samples (n = 149) were collected through online questionnaires and then collected samples were subjected to preliminary data analysis using the IBM SPSS tool to clean the data. Then PLS-SEM method was used to find the relationship between the variables. The study found that strategies are the most significant factor to determine a better work-life balance, though management support, technical support, and organizational culture have relationships between them but that are not significant factors to drive better work-life balance in the post-pandemic era. And the study concluded that if organizations need to more focus on strategies, especially job control, and decision-making strategies then they can maintain a better work-life balance for the IT sector employees in Sri Lanka after the pandemic period.","PeriodicalId":429228,"journal":{"name":"2023 International Research Conference on Smart Computing and Systems Engineering (SCSE)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127857707","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 : 2023-06-29DOI: 10.1109/SCSE59836.2023.10215046
U.M.M.P.K. Nawarathne, H. Kumari
The COVID-19 virus that invaded the world in 2019 caused many casualties while creating enormous mental turmoil among humans. During this pandemic period, humans were confined to prevent the virus from spreading. Due to the isolation, people used social media platforms like Twitter to express their ideas. Therefore, this study analyzed tweets related to COVID-19. Initially, text data processing techniques were employed, and sentiment labels were assigned. Then the data were trained using different machine learning (ML) models such as Multinomial Naïve Bayes (MNB), Random Forest (RF), Support Vector Machine (SVM), Decision Tree (DT), k-Nearest Neighbours (KNN), Logistic Regression (LR), Extreme Gradient Boosting (XGB), and CatBoost (CB). During the training phase, word embedding techniques such as Bag-of-Words (BoW), Term Frequency-Inverse Document Frequency (TF-IDF), Word2Vec, Global Vectors for Word Representation (Glove), Bidirectional Encoder Representations from Transformers (BERT), and Robustly Optimized BERT-Pretraining Approach (RoBERTa) were used, and evaluation metrics such as accuracy, macro average precision, macro average recall, and macro average f1-score were calculated to evaluate these models. According to the results, the CB model, which used the RoBERTa technique, achieved an accuracy of 97%. Therefore, it can be concluded that CB with RoBERTa provides better results when classifying tweet data.
{"title":"A Sentiment Analysis of COVID-19 Tweets Data Using Different Word Embedding Techniques","authors":"U.M.M.P.K. Nawarathne, H. Kumari","doi":"10.1109/SCSE59836.2023.10215046","DOIUrl":"https://doi.org/10.1109/SCSE59836.2023.10215046","url":null,"abstract":"The COVID-19 virus that invaded the world in 2019 caused many casualties while creating enormous mental turmoil among humans. During this pandemic period, humans were confined to prevent the virus from spreading. Due to the isolation, people used social media platforms like Twitter to express their ideas. Therefore, this study analyzed tweets related to COVID-19. Initially, text data processing techniques were employed, and sentiment labels were assigned. Then the data were trained using different machine learning (ML) models such as Multinomial Naïve Bayes (MNB), Random Forest (RF), Support Vector Machine (SVM), Decision Tree (DT), k-Nearest Neighbours (KNN), Logistic Regression (LR), Extreme Gradient Boosting (XGB), and CatBoost (CB). During the training phase, word embedding techniques such as Bag-of-Words (BoW), Term Frequency-Inverse Document Frequency (TF-IDF), Word2Vec, Global Vectors for Word Representation (Glove), Bidirectional Encoder Representations from Transformers (BERT), and Robustly Optimized BERT-Pretraining Approach (RoBERTa) were used, and evaluation metrics such as accuracy, macro average precision, macro average recall, and macro average f1-score were calculated to evaluate these models. According to the results, the CB model, which used the RoBERTa technique, achieved an accuracy of 97%. Therefore, it can be concluded that CB with RoBERTa provides better results when classifying tweet data.","PeriodicalId":429228,"journal":{"name":"2023 International Research Conference on Smart Computing and Systems Engineering (SCSE)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122280690","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 : 2023-06-29DOI: 10.1109/SCSE59836.2023.10215000
Archana Saini, Kalpna Guleria, Shagun Sharma
Early detection of eye diseases is crucial, particularly for individuals with a family history of eye diseases, people over 60 years of age, individuals with diabetes, and those who have a history of eye injuries or surgeries, as they are at a higher risk of developing eye diseases. Early detection and timely treatment are crucial in treating eye diseases and preventing permanent vision loss. Detecting eye diseases early on is crucial in preventing or slowing down the progression of vision loss and blindness. Unfortunately, many eye diseases, including diabetic retinopathy, glaucoma, and cataracts, do not have early warning signs or symptoms. Therefore, regular eye checkups and early detection of these diseases can be essential in preventing vision loss and improving the quality of life for those affected. Retinal fundus image screening is a commonly used technique for diagnosing eye disorders, but manual detection is time-consuming and labour-intensive. To address this issue, various researchers have turned to deep learning methods for the automated detection of retinal eye diseases. In this work, a convolutional neural network model has been developed for classifying eye diseases, demonstrating an impressive accuracy rate of 99.85%. This suggests that the model can correctly classify eye diseases in nearly 4 out of 5 cases. These findings have the potential to significantly improve the accuracy and efficiency of diagnosing eye diseases using retinal fundus images.
{"title":"An Efficient Deep Learning Model for Eye Disease Classification","authors":"Archana Saini, Kalpna Guleria, Shagun Sharma","doi":"10.1109/SCSE59836.2023.10215000","DOIUrl":"https://doi.org/10.1109/SCSE59836.2023.10215000","url":null,"abstract":"Early detection of eye diseases is crucial, particularly for individuals with a family history of eye diseases, people over 60 years of age, individuals with diabetes, and those who have a history of eye injuries or surgeries, as they are at a higher risk of developing eye diseases. Early detection and timely treatment are crucial in treating eye diseases and preventing permanent vision loss. Detecting eye diseases early on is crucial in preventing or slowing down the progression of vision loss and blindness. Unfortunately, many eye diseases, including diabetic retinopathy, glaucoma, and cataracts, do not have early warning signs or symptoms. Therefore, regular eye checkups and early detection of these diseases can be essential in preventing vision loss and improving the quality of life for those affected. Retinal fundus image screening is a commonly used technique for diagnosing eye disorders, but manual detection is time-consuming and labour-intensive. To address this issue, various researchers have turned to deep learning methods for the automated detection of retinal eye diseases. In this work, a convolutional neural network model has been developed for classifying eye diseases, demonstrating an impressive accuracy rate of 99.85%. This suggests that the model can correctly classify eye diseases in nearly 4 out of 5 cases. These findings have the potential to significantly improve the accuracy and efficiency of diagnosing eye diseases using retinal fundus images.","PeriodicalId":429228,"journal":{"name":"2023 International Research Conference on Smart Computing and Systems Engineering (SCSE)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127846755","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：