Human emotion is affected by visual stimuli from all around the environment. This change in emotion and mood carries over to our tastes in various things, one of them being music. Computer vision and data mining are sub-fields of computer science that deal with the interpretation of visual media and analysis of temporal data to derive an outcome respectively. There has yet to be a method of interpreting visual media and associating it with any sort of music genre. Computer vision can be utilized to recognize the effect of visual elements of the environment on human emotion while data mining can be used to suggest appropriate music genres based on that emotion. This is the approach our paper used to solve the aforementioned problem.In this paper, we have used different models to interpret different attributes from a given image. In our implementation, five attributes were identified and five models were used to detect them. A few surveys were conducted to get a pattern in people’s taste in music according to visual stimuli. The results from the surveys were then used to recommend a music genre from the processed combination of attributes mentioned before. This shall provide a starting point and motivate further research of its kind.
{"title":"Music Suggestions from Determining the Atmosphere of Images","authors":"Saiful Islam Sohel, Chinmoy Mondol, Hassan Shahriar Ayon, Urmi Tasmim Islam, Md. Kishor Morol","doi":"10.1109/ICCIT54785.2021.9689781","DOIUrl":"https://doi.org/10.1109/ICCIT54785.2021.9689781","url":null,"abstract":"Human emotion is affected by visual stimuli from all around the environment. This change in emotion and mood carries over to our tastes in various things, one of them being music. Computer vision and data mining are sub-fields of computer science that deal with the interpretation of visual media and analysis of temporal data to derive an outcome respectively. There has yet to be a method of interpreting visual media and associating it with any sort of music genre. Computer vision can be utilized to recognize the effect of visual elements of the environment on human emotion while data mining can be used to suggest appropriate music genres based on that emotion. This is the approach our paper used to solve the aforementioned problem.In this paper, we have used different models to interpret different attributes from a given image. In our implementation, five attributes were identified and five models were used to detect them. A few surveys were conducted to get a pattern in people’s taste in music according to visual stimuli. The results from the surveys were then used to recommend a music genre from the processed combination of attributes mentioned before. This shall provide a starting point and motivate further research of its kind.","PeriodicalId":166450,"journal":{"name":"2021 24th International Conference on Computer and Information Technology (ICCIT)","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126557644","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 image tagging task aims to assign relevant known tags to an image. It is an active research topic in computer vision and machine learning because of the diversity of its applications in semantic search and image retrieval. Earlier efforts on image tagging address this problem as a multi-level classification problem using visual features from images and semantic word vectors of tags. In most cases, a pre-trained language model like word2vec or Globe is used to obtain those word vectors. Because of using a pre-trained language model, an image tagging approach cannot scale itself to the context of the targeted application. This paper fine-tunes a language (BERT) model using text descriptions obtained from web (Wikipedia) scraping to learn a rich distributed representation of tags. Then, we employ word vectors of tags extracted from finetuned language (BERT) model to solve the image tagging task. Our method is more specialized to the particular application by incorporating context information between targeted tags and images. As a result, word vectors obtained from the fine-tuned model perform better than those from pre-trained language models. We evaluate our method on the widely used NUS-WIDE dataset and achieve competitive results compared with state-of-the-art methods.
{"title":"Image Tagging by Fine-tuning Class Semantics Using Text Data from Web Scraping","authors":"Mehedi Hasan Bijoy, Nirob Hasan, Md. Tahrim Faroque Tushar, Shafin Rahmany","doi":"10.1109/ICCIT54785.2021.9689793","DOIUrl":"https://doi.org/10.1109/ICCIT54785.2021.9689793","url":null,"abstract":"The image tagging task aims to assign relevant known tags to an image. It is an active research topic in computer vision and machine learning because of the diversity of its applications in semantic search and image retrieval. Earlier efforts on image tagging address this problem as a multi-level classification problem using visual features from images and semantic word vectors of tags. In most cases, a pre-trained language model like word2vec or Globe is used to obtain those word vectors. Because of using a pre-trained language model, an image tagging approach cannot scale itself to the context of the targeted application. This paper fine-tunes a language (BERT) model using text descriptions obtained from web (Wikipedia) scraping to learn a rich distributed representation of tags. Then, we employ word vectors of tags extracted from finetuned language (BERT) model to solve the image tagging task. Our method is more specialized to the particular application by incorporating context information between targeted tags and images. As a result, word vectors obtained from the fine-tuned model perform better than those from pre-trained language models. We evaluate our method on the widely used NUS-WIDE dataset and achieve competitive results compared with state-of-the-art methods.","PeriodicalId":166450,"journal":{"name":"2021 24th International Conference on Computer and Information Technology (ICCIT)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124684101","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 : 2021-12-18DOI: 10.1109/ICCIT54785.2021.9689823
Abu Saleh Bin Shahadat, Safial Islam Ayon, M. R. Khatun
Many approaches have been developed to make intelligent moves imitating rational decision-makers. Game theory provides a theoretical framework that can be efficiently employed in solving complex optimization problems. The area of applied mathematics that investigates the strategic behavior of rational factors is known as game theory. In other terms, game theory is an analytical tool for making the optimal decision in interaction and decision-making situations. The Traveling Salesman Problem (TSP) is solved using this research’s swap sequence-based game theory algorithm (SSGTA). TSP is a well-known combinatorial optimization real problem. TSP is also widely used to assess expertise in newly emerging optimization techniques. Furthermore, optimization techniques established for other tasks (such as numerical optimization) are tested for TSP competency. A player attempts to update its solution using another player. An expected payoff mechanism is proposed to choose the learning strategy. Based on the improvement of solution quality, a payoff is awarded to the winning player. When no improvement is noticed in the solution, the 2-opt algorithm is employed to get over the local optimal. SSGTA is tested for several benchmark TSP instances from TSPLIB and compared with some other recent methods. SSGTA performs better than different algorithms on accuracy and stability.
{"title":"SSGTA: A Novel Swap Sequence based Game Theory Algorithm for Traveling Salesman Problem","authors":"Abu Saleh Bin Shahadat, Safial Islam Ayon, M. R. Khatun","doi":"10.1109/ICCIT54785.2021.9689823","DOIUrl":"https://doi.org/10.1109/ICCIT54785.2021.9689823","url":null,"abstract":"Many approaches have been developed to make intelligent moves imitating rational decision-makers. Game theory provides a theoretical framework that can be efficiently employed in solving complex optimization problems. The area of applied mathematics that investigates the strategic behavior of rational factors is known as game theory. In other terms, game theory is an analytical tool for making the optimal decision in interaction and decision-making situations. The Traveling Salesman Problem (TSP) is solved using this research’s swap sequence-based game theory algorithm (SSGTA). TSP is a well-known combinatorial optimization real problem. TSP is also widely used to assess expertise in newly emerging optimization techniques. Furthermore, optimization techniques established for other tasks (such as numerical optimization) are tested for TSP competency. A player attempts to update its solution using another player. An expected payoff mechanism is proposed to choose the learning strategy. Based on the improvement of solution quality, a payoff is awarded to the winning player. When no improvement is noticed in the solution, the 2-opt algorithm is employed to get over the local optimal. SSGTA is tested for several benchmark TSP instances from TSPLIB and compared with some other recent methods. SSGTA performs better than different algorithms on accuracy and stability.","PeriodicalId":166450,"journal":{"name":"2021 24th International Conference on Computer and Information Technology (ICCIT)","volume":"79 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128565370","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 : 2021-11-22DOI: 10.1109/ICCIT54785.2021.9689824
Quazi Adibur Rahman Adib, Sidratul Tanzila Tasmi, Md. Shahriar Islam Bhuiyan, M. Raihan, A. Shams
COVID-19 pandemic is an ongoing global pandemic which has caused unprecedented disruptions in the public health sector and global economy. The virus, SARS-CoV-2 is responsible for the rapid transmission of coronavirus disease. Due to its contagious nature, the virus can easily infect an unprotected and exposed individual from mild to severe symptoms. The study of the virus’s effects on pregnant mothers and neonatal is now a concerning issue globally among civilians and public health workers considering how the virus will affect the mother and the neonate’s health. This paper aims to develop a predictive model to estimate the possibility of death for a COVID-diagnosed mother based on documented symptoms: dyspnea, cough, rhinorrhea, arthralgia, and the diagnosis of pneumonia. The machine learning models that have been used in our study are support vector machine, decision tree, random forest, gradient boosting, and artificial neural network. The models have provided impressive results and can accurately predict the mortality of pregnant mother’s with a given input. The precision rate for 3 models(ANN, Gradient Boost, Random Forest) is 100% The highest accuracy score(Gradient Boosting, ANN) is 95%, highest recall(Support Vector Machine) is 92.75% and highest f1 score(Gradient Boosting, ANN) is 94.66%. Due to the accuracy of the model, pregnant mother can expect immediate medical treatment based on their possibility of death due to the virus. The model can be utilized by health workers globally to list down emergency patients, which can ultimately reduce the death rate of COVID-19 diagnosed pregnant mothers.
{"title":"Prediction Model for Mortality Analysis of Pregnant Women Affected With COVID-19","authors":"Quazi Adibur Rahman Adib, Sidratul Tanzila Tasmi, Md. Shahriar Islam Bhuiyan, M. Raihan, A. Shams","doi":"10.1109/ICCIT54785.2021.9689824","DOIUrl":"https://doi.org/10.1109/ICCIT54785.2021.9689824","url":null,"abstract":"COVID-19 pandemic is an ongoing global pandemic which has caused unprecedented disruptions in the public health sector and global economy. The virus, SARS-CoV-2 is responsible for the rapid transmission of coronavirus disease. Due to its contagious nature, the virus can easily infect an unprotected and exposed individual from mild to severe symptoms. The study of the virus’s effects on pregnant mothers and neonatal is now a concerning issue globally among civilians and public health workers considering how the virus will affect the mother and the neonate’s health. This paper aims to develop a predictive model to estimate the possibility of death for a COVID-diagnosed mother based on documented symptoms: dyspnea, cough, rhinorrhea, arthralgia, and the diagnosis of pneumonia. The machine learning models that have been used in our study are support vector machine, decision tree, random forest, gradient boosting, and artificial neural network. The models have provided impressive results and can accurately predict the mortality of pregnant mother’s with a given input. The precision rate for 3 models(ANN, Gradient Boost, Random Forest) is 100% The highest accuracy score(Gradient Boosting, ANN) is 95%, highest recall(Support Vector Machine) is 92.75% and highest f1 score(Gradient Boosting, ANN) is 94.66%. Due to the accuracy of the model, pregnant mother can expect immediate medical treatment based on their possibility of death due to the virus. The model can be utilized by health workers globally to list down emergency patients, which can ultimately reduce the death rate of COVID-19 diagnosed pregnant mothers.","PeriodicalId":166450,"journal":{"name":"2021 24th International Conference on Computer and Information Technology (ICCIT)","volume":"18 6","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133169960","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 : 2021-11-19DOI: 10.1109/ICCIT54785.2021.9689852
Nobel Dhar, Gaurob Saha, Prithwiraj Bhattacharjee, Avi Mallick, Md. Saiful Islam
Despite the success of the neural sequence-to-sequence model for abstractive text summarization, it has a few shortcomings, such as repeating inaccurate factual details and tending to repeat themselves. We propose a hybrid pointer generator network to solve the shortcomings of reproducing factual details inadequately and phrase repetition. We augment the attention-based sequence-to-sequence using a hybrid pointer generator network that can generate Out-of-Vocabulary words and enhance accuracy in reproducing authentic details and a coverage mechanism that discourages repetition. It produces a reasonable-sized output text that preserves the conceptual integrity and factual information of the input article. For evaluation, we primarily employed “BANSData”1 - a highly adopted publicly available Bengali dataset. Additionally, we prepared a large-scale dataset called “BANS-133” which consists of 133k Bangla news articles associated with human-generated summaries. Experimenting with the proposed model, we achieved ROUGE-1 and ROUGE-2 scores of 0.66, 0.41 for the BANSData” dataset and 0.67, 0.42 for the BANS-133k” dataset, respectively. We demonstrated that the proposed system surpasses previous state-of-the-art Bengali abstractive summarization techniques and its stability on a larger dataset. “BANS-133” datasets and code-base will be publicly available for research.
{"title":"Pointer over Attention: An Improved Bangla Text Summarization Approach Using Hybrid Pointer Generator Network","authors":"Nobel Dhar, Gaurob Saha, Prithwiraj Bhattacharjee, Avi Mallick, Md. Saiful Islam","doi":"10.1109/ICCIT54785.2021.9689852","DOIUrl":"https://doi.org/10.1109/ICCIT54785.2021.9689852","url":null,"abstract":"Despite the success of the neural sequence-to-sequence model for abstractive text summarization, it has a few shortcomings, such as repeating inaccurate factual details and tending to repeat themselves. We propose a hybrid pointer generator network to solve the shortcomings of reproducing factual details inadequately and phrase repetition. We augment the attention-based sequence-to-sequence using a hybrid pointer generator network that can generate Out-of-Vocabulary words and enhance accuracy in reproducing authentic details and a coverage mechanism that discourages repetition. It produces a reasonable-sized output text that preserves the conceptual integrity and factual information of the input article. For evaluation, we primarily employed “BANSData”1 - a highly adopted publicly available Bengali dataset. Additionally, we prepared a large-scale dataset called “BANS-133” which consists of 133k Bangla news articles associated with human-generated summaries. Experimenting with the proposed model, we achieved ROUGE-1 and ROUGE-2 scores of 0.66, 0.41 for the BANSData” dataset and 0.67, 0.42 for the BANS-133k” dataset, respectively. We demonstrated that the proposed system surpasses previous state-of-the-art Bengali abstractive summarization techniques and its stability on a larger dataset. “BANS-133” datasets and code-base will be publicly available for research.","PeriodicalId":166450,"journal":{"name":"2021 24th International Conference on Computer and Information Technology (ICCIT)","volume":"282 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132094917","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 : 2021-08-09DOI: 10.1109/ICCIT54785.2021.9689896
Al Maruf Hassan, Istiak Ahmed Mondal
Pedagogy is a method that handles the ethos and culture of instruction from teachers and the way of learning of learners. Pedagogy of Information and Communications Technology (ICT) deals with the interconnection among the teacher, children, and educational atmosphere based on ICT. It is a discipline that deals with the theory and practice of teaching strategies, teaching actions, teaching judgments, and decisions. In this paper, we have constructed the pedagogical learning environment from various perspectives of ICT education. In our methodology, covers the pedagogy for ICT education includes the interaction among different elements. The methodology improves to propagate convenience differently into the educational environment. We have built a hybrid model for the ICT development program. The hybrid model represents the combination of standards, stages, year level, class level, and age level. It brings the curriculum into one umbrella and makes the hypothesis for borderless curriculum exchange among Australian Capital Territory (ACT), Tasmania (TAS), and Bangladesh for the children between the age of 3 to 18. We have constructed the pedagogical learning environment theoretically from the perspective of ICT education to the consideration of the outcome for each element of our proposed architecture. We consider the proposed architecture to build a global standard procedure through the pedagogical learning environment of ICT education both physically and virtually.
{"title":"Modeling Pedagogical Learning Environment with Hybrid Model based on ICT","authors":"Al Maruf Hassan, Istiak Ahmed Mondal","doi":"10.1109/ICCIT54785.2021.9689896","DOIUrl":"https://doi.org/10.1109/ICCIT54785.2021.9689896","url":null,"abstract":"Pedagogy is a method that handles the ethos and culture of instruction from teachers and the way of learning of learners. Pedagogy of Information and Communications Technology (ICT) deals with the interconnection among the teacher, children, and educational atmosphere based on ICT. It is a discipline that deals with the theory and practice of teaching strategies, teaching actions, teaching judgments, and decisions. In this paper, we have constructed the pedagogical learning environment from various perspectives of ICT education. In our methodology, covers the pedagogy for ICT education includes the interaction among different elements. The methodology improves to propagate convenience differently into the educational environment. We have built a hybrid model for the ICT development program. The hybrid model represents the combination of standards, stages, year level, class level, and age level. It brings the curriculum into one umbrella and makes the hypothesis for borderless curriculum exchange among Australian Capital Territory (ACT), Tasmania (TAS), and Bangladesh for the children between the age of 3 to 18. We have constructed the pedagogical learning environment theoretically from the perspective of ICT education to the consideration of the outcome for each element of our proposed architecture. We consider the proposed architecture to build a global standard procedure through the pedagogical learning environment of ICT education both physically and virtually.","PeriodicalId":166450,"journal":{"name":"2021 24th International Conference on Computer and Information Technology (ICCIT)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-08-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125446970","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：