The digitized environments are particularly vulnerable to various attacks. In such a situation of a security attack, detecting and responding to attacks require effective actions. One of the most significant ways to improve resilience to security attacks is to obtain accurate and timely situational aspect of the security awareness. The efficient production and utilization of situation information is achieved by sharing information with other actors in the information sharing network quickly and reliably without compromising the confidential information of one's own organization. At the same time, it should also be possible to avoid a flood of irrelevant information in the sharing network, which wastes resources and slows down the implementation of security measures. In our study, we have investigated how security-related information can be shared online as efficiently as possible by building a security information sharing topology based on the two most widely used network optimization algorithms. In the article, we present a model of an information sharing network, in which three different parameters have been used to optimize the network topology: the activity level of organization, the similarity of information systems between different actors and the requirement for the level of information privacy generally in the organization.
{"title":"A model of Cyber Threat Information Sharing with the Novel Network Topology","authors":"J. Hautamaki, T. Hamalainen","doi":"10.1145/3468784.3468885","DOIUrl":"https://doi.org/10.1145/3468784.3468885","url":null,"abstract":"The digitized environments are particularly vulnerable to various attacks. In such a situation of a security attack, detecting and responding to attacks require effective actions. One of the most significant ways to improve resilience to security attacks is to obtain accurate and timely situational aspect of the security awareness. The efficient production and utilization of situation information is achieved by sharing information with other actors in the information sharing network quickly and reliably without compromising the confidential information of one's own organization. At the same time, it should also be possible to avoid a flood of irrelevant information in the sharing network, which wastes resources and slows down the implementation of security measures. In our study, we have investigated how security-related information can be shared online as efficiently as possible by building a security information sharing topology based on the two most widely used network optimization algorithms. In the article, we present a model of an information sharing network, in which three different parameters have been used to optimize the network topology: the activity level of organization, the similarity of information systems between different actors and the requirement for the level of information privacy generally in the organization.","PeriodicalId":341589,"journal":{"name":"The 12th International Conference on Advances in Information Technology","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128257863","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 benefits of effectively visualizing health records in huge volumes has resulted in health organizations, insurance companies, policy and decision makers, governments and drug manufactures’ transformation in the way research is conducted. This has also played a key role in determining investment of resources. Health records contain highly valuable information; processing these records in large volumes is now possible due to technological advancement which allows for the extraction of highly valuable knowledge that has resulted in breakthroughs in scientific communities. To visualize health records in large volumes, the records need to be stored in electronic forms, properly documented, processed, and analyzed. A good visualization technique is used to present the analyzed information, allowing for effective knowledge extraction which is done in a secured manner protecting the privacy of the patients whose health records were used. As research and technological advancement have improved, the quality of knowledge extracted from health records have also improved; unfortunately, the numerous benefits of visualizing health records have only been felt in developed nations, unlike other sectors where technological advancement in developed nations have had similar impact in developing nations. This paper identifies the characteristics of health records and the challenges involved in processing large volumes of health records. This is to identify possible steps that could be taken for developing nations to benefit from visualizing health records in huge volumes.
{"title":"Visualising Developing Nations Health Records: Opportunities, Challenges and Research Agenda","authors":"Afamefuna Umejiaku, Tommy Dang","doi":"10.1145/3468784.3471607","DOIUrl":"https://doi.org/10.1145/3468784.3471607","url":null,"abstract":"The benefits of effectively visualizing health records in huge volumes has resulted in health organizations, insurance companies, policy and decision makers, governments and drug manufactures’ transformation in the way research is conducted. This has also played a key role in determining investment of resources. Health records contain highly valuable information; processing these records in large volumes is now possible due to technological advancement which allows for the extraction of highly valuable knowledge that has resulted in breakthroughs in scientific communities. To visualize health records in large volumes, the records need to be stored in electronic forms, properly documented, processed, and analyzed. A good visualization technique is used to present the analyzed information, allowing for effective knowledge extraction which is done in a secured manner protecting the privacy of the patients whose health records were used. As research and technological advancement have improved, the quality of knowledge extracted from health records have also improved; unfortunately, the numerous benefits of visualizing health records have only been felt in developed nations, unlike other sectors where technological advancement in developed nations have had similar impact in developing nations. This paper identifies the characteristics of health records and the challenges involved in processing large volumes of health records. This is to identify possible steps that could be taken for developing nations to benefit from visualizing health records in huge volumes.","PeriodicalId":341589,"journal":{"name":"The 12th International Conference on Advances in Information Technology","volume":"41 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127883668","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}
Shafinul Haque, A. Liu, Serena Liu, Jonathan H. Chan
Deep convolutional neural networks trained on readily available datasets are often susceptible to decreases in performance when executing tasks on new data from a different domain. Making models generalize well on data in a new domain is the task of domain adaptation. Recently, a simple method, known as Out-of-Distribution Image Detector for Neural Networks (ODIN), was proposed for identifying out-of-distribution (OOD) images in a dataset. This paper proposes fine-tuning an image classifier model using OOD images detected in an ideal training set to improve the model's ability to classify real-life images. This work aims to investigate the effectiveness of such a technique, as well as image preprocessing methods like background removal and image cropping, at increasing the robustness of a ResNet50V2 baseline image classifier in the context of a multi-class classification task. It was observed that fine-tuning with OOD images identified by ODIN consistently increased the model's performance and that a combination of cropping images and fine-tuning with OOD images resulted in the greatest increase in the model's performance.
{"title":"Improving the Robustness of a Convolutional Neural Network with Out-of-Distribution Data Fine-Tuning and Image Preprocessing","authors":"Shafinul Haque, A. Liu, Serena Liu, Jonathan H. Chan","doi":"10.1145/3468784.3470655","DOIUrl":"https://doi.org/10.1145/3468784.3470655","url":null,"abstract":"Deep convolutional neural networks trained on readily available datasets are often susceptible to decreases in performance when executing tasks on new data from a different domain. Making models generalize well on data in a new domain is the task of domain adaptation. Recently, a simple method, known as Out-of-Distribution Image Detector for Neural Networks (ODIN), was proposed for identifying out-of-distribution (OOD) images in a dataset. This paper proposes fine-tuning an image classifier model using OOD images detected in an ideal training set to improve the model's ability to classify real-life images. This work aims to investigate the effectiveness of such a technique, as well as image preprocessing methods like background removal and image cropping, at increasing the robustness of a ResNet50V2 baseline image classifier in the context of a multi-class classification task. It was observed that fine-tuning with OOD images identified by ODIN consistently increased the model's performance and that a combination of cropping images and fine-tuning with OOD images resulted in the greatest increase in the model's performance.","PeriodicalId":341589,"journal":{"name":"The 12th International Conference on Advances in Information Technology","volume":"71 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122953040","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 proposes OutViz, a dual view framework for representing and filtering multivariate time series data to highlight abnormal patterns in a dataset. The first view of the proposed visualization incorporates a parallel coordinate chart that allows the user to analyze the scores of features extracted from a dimensionality reduction density-based clustering outlier detection algorithm to determine why a particular time series is predicted to be an outlier. Also included on the parallel coordinates chart is an outlier score rank axis that allows the user to select a range of time series data to be filtered and displayed on the second view of the framework. The second view of our proposed framework uses a multi-line chart to represent how each time series variable changes over a range of time. Each time series is represented as a line with the position on the horizontal axis representing a point in time, while the vertical axis encodes the data value. Use cases using real-world multivariate time series data are demonstrated to show the advantages of using the proposed framework for data analytics as well as some findings uncovered while using OutViz on life expectancy data from 236 countries between the year 1960 and 2018, and carbon dioxide emissions data from 210 countries between the year 1960 and 2016.
{"title":"OutViz: Visualizing the Outliers of Multivariate Time Series","authors":"Jake Gonzalez, Tommy Dang","doi":"10.1145/3468784.3471606","DOIUrl":"https://doi.org/10.1145/3468784.3471606","url":null,"abstract":"This paper proposes OutViz, a dual view framework for representing and filtering multivariate time series data to highlight abnormal patterns in a dataset. The first view of the proposed visualization incorporates a parallel coordinate chart that allows the user to analyze the scores of features extracted from a dimensionality reduction density-based clustering outlier detection algorithm to determine why a particular time series is predicted to be an outlier. Also included on the parallel coordinates chart is an outlier score rank axis that allows the user to select a range of time series data to be filtered and displayed on the second view of the framework. The second view of our proposed framework uses a multi-line chart to represent how each time series variable changes over a range of time. Each time series is represented as a line with the position on the horizontal axis representing a point in time, while the vertical axis encodes the data value. Use cases using real-world multivariate time series data are demonstrated to show the advantages of using the proposed framework for data analytics as well as some findings uncovered while using OutViz on life expectancy data from 236 countries between the year 1960 and 2018, and carbon dioxide emissions data from 210 countries between the year 1960 and 2016.","PeriodicalId":341589,"journal":{"name":"The 12th International Conference on Advances in Information Technology","volume":"83 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114804416","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}
Kanittha Rungyaem, K. Sukvichai, T. Phatrapornnant
The rice breeding produces the high-throughput via a genotyping technology. It can rapidly test and analyze on a large number of samples while the performance of phenotypic evaluation is still very low because of the manually evaluation. Therefore, this is the main barrier retarding the new rice varieties development. This research is aimed to develop a method for classifying plant organs from 3D point cloud in order to analyze plant morphology or architecture automatically. The rice plant was scanned with a 3D laser scan machine. The points in the cloud were reduced by the skeleton skimming method because the number of points in each cloud group is too large. Thus, it is necessary to preprocess before importing into neural networks for classification. The PointNet was selected as the 3D classifier in this research. The first experiment was conducted in order to evaluate the proposed method. The result showed that the proposed method can classify rice organs, regardless of rice varieties, with accuracy of 87.04%. Then, the second experiment was conducted in order to obtain the accuracy of the network for each rice variety to demonstrate the influence of rice cultivars in the classification due to their different shapes. The results showed that the SPRLR, which had large numbers of leaves and yield, has the lowest accuracy of 51.61% while the other varieties with the greater leaf and panicle distribution have a much better accuracy. The Nieow dum had 91.16% accuracy while Jae hwa, Kaow lueng and Kam had 89.06%, 86.52% and 75.22% accuracy respectively.
{"title":"The 3-dimensional Plant Organs Point Clouds Classification for the Phenotyping Application based on CNNs.","authors":"Kanittha Rungyaem, K. Sukvichai, T. Phatrapornnant","doi":"10.1145/3468784.3469949","DOIUrl":"https://doi.org/10.1145/3468784.3469949","url":null,"abstract":"The rice breeding produces the high-throughput via a genotyping technology. It can rapidly test and analyze on a large number of samples while the performance of phenotypic evaluation is still very low because of the manually evaluation. Therefore, this is the main barrier retarding the new rice varieties development. This research is aimed to develop a method for classifying plant organs from 3D point cloud in order to analyze plant morphology or architecture automatically. The rice plant was scanned with a 3D laser scan machine. The points in the cloud were reduced by the skeleton skimming method because the number of points in each cloud group is too large. Thus, it is necessary to preprocess before importing into neural networks for classification. The PointNet was selected as the 3D classifier in this research. The first experiment was conducted in order to evaluate the proposed method. The result showed that the proposed method can classify rice organs, regardless of rice varieties, with accuracy of 87.04%. Then, the second experiment was conducted in order to obtain the accuracy of the network for each rice variety to demonstrate the influence of rice cultivars in the classification due to their different shapes. The results showed that the SPRLR, which had large numbers of leaves and yield, has the lowest accuracy of 51.61% while the other varieties with the greater leaf and panicle distribution have a much better accuracy. The Nieow dum had 91.16% accuracy while Jae hwa, Kaow lueng and Kam had 89.06%, 86.52% and 75.22% accuracy respectively.","PeriodicalId":341589,"journal":{"name":"The 12th International Conference on Advances in Information Technology","volume":"45 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122641235","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}
Visualizations are context-specific. Understanding the context of visualizations before deciding to use them is a daunting task since users have various backgrounds, and there are thousands of available visual representations (and their variances). To this end, this paper proposes a visual analytics framework to achieve the following research goals: (1) to automatically generate a number of suitable representations for visualizing the input data and present it to users as a catalog of visualizations with different levels of abstractions and data characteristics on one/two/multi-dimensional spaces (2) to infer aspects of the user’s interest based on their interactions (3) to narrow down a smaller set of visualizations that suit users analysis intention. The results of this process give our analytics system the means to better understand the user’s analysis process and enable it to better provide timely recommendations.
{"title":"HMaViz: Human-machine analytics for visual recommendation","authors":"Ngan V. T. Nguyen, Vung V. Pham, Tommy Dang","doi":"10.1145/3468784.3471601","DOIUrl":"https://doi.org/10.1145/3468784.3471601","url":null,"abstract":"Visualizations are context-specific. Understanding the context of visualizations before deciding to use them is a daunting task since users have various backgrounds, and there are thousands of available visual representations (and their variances). To this end, this paper proposes a visual analytics framework to achieve the following research goals: (1) to automatically generate a number of suitable representations for visualizing the input data and present it to users as a catalog of visualizations with different levels of abstractions and data characteristics on one/two/multi-dimensional spaces (2) to infer aspects of the user’s interest based on their interactions (3) to narrow down a smaller set of visualizations that suit users analysis intention. The results of this process give our analytics system the means to better understand the user’s analysis process and enable it to better provide timely recommendations.","PeriodicalId":341589,"journal":{"name":"The 12th International Conference on Advances in Information Technology","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125865080","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}
Corona viruses (CoVs) are a group of infectious viruses that causes the regular cold to more extreme illnesses like Middle East Respiratory Syndrome (MERS-CoV), Severe Acute Respiratory Syndrome (SARS-CoV) and epic Covid (nCoV) is another strain that has been recently recognized in people. The formulation of effective drugs and treatment strategies are desperately required for 2019-nCoV/SARS-CoV-2 outbreak. Reducing the clinical trial period of existing as well as new drugs, the phytochemicals present in natural products would be helpful to get a quick treatment solution for this pandemic. Here, computationally some of the effective phytochemicals are identified for treating Covid. Publicly available databases have been used for collecting the phytochemicals and their associated genes that also interact with Corona viruses. Then a bipartite graph has been built with two sets of inputs; one set is the set of phytochemicals and the second set is the set of viruses. Thereafter, the eigen vector centrality which is the measure of most influential node in a graph has been calculated for each phytochemical. We found four such phytochemicals which have the top four eigen vector score. Then again, all possible cliques from the bipartite graph have been calculated and it has been seen that the same top four phytochemicals are present in almost all the bicliques. Finally, these top four phytochemicals have been investigated for their molecular and drug likeliness properties. Also the ADMET profile of the top phytochemicals are explored and analyzed.
{"title":"Phytochemicals as potential inhibitors for novel coronavirus 2019-nCoV/SARS-CoV-2: a graph-based computational analysis","authors":"M. Mandal","doi":"10.1145/3468784.3468886","DOIUrl":"https://doi.org/10.1145/3468784.3468886","url":null,"abstract":"Corona viruses (CoVs) are a group of infectious viruses that causes the regular cold to more extreme illnesses like Middle East Respiratory Syndrome (MERS-CoV), Severe Acute Respiratory Syndrome (SARS-CoV) and epic Covid (nCoV) is another strain that has been recently recognized in people. The formulation of effective drugs and treatment strategies are desperately required for 2019-nCoV/SARS-CoV-2 outbreak. Reducing the clinical trial period of existing as well as new drugs, the phytochemicals present in natural products would be helpful to get a quick treatment solution for this pandemic. Here, computationally some of the effective phytochemicals are identified for treating Covid. Publicly available databases have been used for collecting the phytochemicals and their associated genes that also interact with Corona viruses. Then a bipartite graph has been built with two sets of inputs; one set is the set of phytochemicals and the second set is the set of viruses. Thereafter, the eigen vector centrality which is the measure of most influential node in a graph has been calculated for each phytochemical. We found four such phytochemicals which have the top four eigen vector score. Then again, all possible cliques from the bipartite graph have been calculated and it has been seen that the same top four phytochemicals are present in almost all the bicliques. Finally, these top four phytochemicals have been investigated for their molecular and drug likeliness properties. Also the ADMET profile of the top phytochemicals are explored and analyzed.","PeriodicalId":341589,"journal":{"name":"The 12th International Conference on Advances in Information Technology","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126516354","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}
Debasrita Chakraborty, Debayan Goswami, Ashish Ghosh, Jonathan H. Chan, Susmita K. Ghosh
Accurate prediction of the number of COVID-19 infected cases per day is fast becoming a critical necessity globally to mitigate the burden on various health systems. In a densely populated country like India which has currently the second highest number of infections and limited medical support, it is a need for the authorities to know the statistics beforehand to address these issues more effectively. In this article, a data driven transfer learning based model is proposed that takes into account the conditions of different countries which have witnessed the COVID-19 infection. We have taken four countries to be the source domain for transfer learning scenario namely, the United States of America, Spain, Brazil and Bangladesh. We have pre-trained four different LSTM-RNN models with each of the country’s data and have re-trained (fine tuned) each of the models using only a very small portion of Indian data on COVID-19. Predictions of these four models are averaged to get the actual prediction. It is seen that such an ensemble model outperforms all the compared models and accurately predicts even the daily cases. This may be due to the fact that the four LSTM-RNNs used here could successfully take into account the diversities of conditions. As India is a diverse nation with variety of climates, it makes more sense to incorporate such transfer learning techniques.
{"title":"Learning from Others: A Data Driven Transfer Learning based Daily New COVID-19 Case Prediction in India using an Ensemble of LSTM-RNNs","authors":"Debasrita Chakraborty, Debayan Goswami, Ashish Ghosh, Jonathan H. Chan, Susmita K. Ghosh","doi":"10.1145/3468784.3470769","DOIUrl":"https://doi.org/10.1145/3468784.3470769","url":null,"abstract":"Accurate prediction of the number of COVID-19 infected cases per day is fast becoming a critical necessity globally to mitigate the burden on various health systems. In a densely populated country like India which has currently the second highest number of infections and limited medical support, it is a need for the authorities to know the statistics beforehand to address these issues more effectively. In this article, a data driven transfer learning based model is proposed that takes into account the conditions of different countries which have witnessed the COVID-19 infection. We have taken four countries to be the source domain for transfer learning scenario namely, the United States of America, Spain, Brazil and Bangladesh. We have pre-trained four different LSTM-RNN models with each of the country’s data and have re-trained (fine tuned) each of the models using only a very small portion of Indian data on COVID-19. Predictions of these four models are averaged to get the actual prediction. It is seen that such an ensemble model outperforms all the compared models and accurately predicts even the daily cases. This may be due to the fact that the four LSTM-RNNs used here could successfully take into account the diversities of conditions. As India is a diverse nation with variety of climates, it makes more sense to incorporate such transfer learning techniques.","PeriodicalId":341589,"journal":{"name":"The 12th International Conference on Advances in Information Technology","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131277219","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}
Sound plays a vital role in every aspect of human life since it is one of the primary sensory information that our auditory system collects and allows us to perceive the world. Sound clustering and visualization is the process of collecting and analyzing audio samples; that process is a prerequisite of sound classification, which is the core of automatic speech recognition, virtual assistants, and text to speech applications. Nevertheless, understanding how to recognize and properly interpret complex, high-dimensional audio data is the most significant challenge in sound clustering and visualization. This paper proposed a web-based platform to visualize and cluster similar sound samples of musical notes and human speech in real-time. For visualizing high-dimensional data like audio, Mel-Frequency Cepstral Coefficients (MFCCs) were initially developed to represent the sounds made by the human vocal tract are extracted. Then, t-distributed Stochastic Neighbor Embedding (t-SNE), a dimensionality reduction technique, was designed for high dimensional datasets is applied. This paper focuses on both data clustering and high-dimensional visualization methods to properly present the clustering results in the most meaningful way to uncover potentially interesting behavioral patterns of musical notes played by different instruments.
{"title":"Real-time Sound Visualization via Multidimensional Clustering and Projections","authors":"N. Le, Ngan V. T. Nguyen, Tommy Dang","doi":"10.1145/3468784.3471604","DOIUrl":"https://doi.org/10.1145/3468784.3471604","url":null,"abstract":"Sound plays a vital role in every aspect of human life since it is one of the primary sensory information that our auditory system collects and allows us to perceive the world. Sound clustering and visualization is the process of collecting and analyzing audio samples; that process is a prerequisite of sound classification, which is the core of automatic speech recognition, virtual assistants, and text to speech applications. Nevertheless, understanding how to recognize and properly interpret complex, high-dimensional audio data is the most significant challenge in sound clustering and visualization. This paper proposed a web-based platform to visualize and cluster similar sound samples of musical notes and human speech in real-time. For visualizing high-dimensional data like audio, Mel-Frequency Cepstral Coefficients (MFCCs) were initially developed to represent the sounds made by the human vocal tract are extracted. Then, t-distributed Stochastic Neighbor Embedding (t-SNE), a dimensionality reduction technique, was designed for high dimensional datasets is applied. This paper focuses on both data clustering and high-dimensional visualization methods to properly present the clustering results in the most meaningful way to uncover potentially interesting behavioral patterns of musical notes played by different instruments.","PeriodicalId":341589,"journal":{"name":"The 12th International Conference on Advances in Information Technology","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132710308","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}
Personality Traits are important customer insights for business. Persuasive messages in advertising campaigns are more effective when customized to fit the customers' personalities. Researches suggested that music preference can reflect personality traits. However, those studies collected music listening history by using self-report of which the data obtained can be incomplete. This research aims to increase the completeness of music listening data by conducting a study on the three-month music streaming history of volunteers recorded automatically by Spotify. The eight audio features of each song (Acousticness, Danceability, Energy, Instrumentalness, Liveness, Speechiness, Valence, and Tempo) were extracted using Spotify's Application Programming Interface. The averages of these features calculated from songs in the music streaming history of each volunteer were used to represent his music preference. Pearson's Correlation method was employed to analyze relationships between the Big 5 Personality Traits and the music preference of 40 volunteers. The result shows a positive correlation between Openness-to-Experience and Liveness, a positive correlation between Extraversion and Acousticness, and a negative correlation between Extraversion with Energy and Speechiness. Agreeableness shows a positive correlation with Tempo. Instrumentalness is the only song feature that has a positive correlation with Neuroticism.
{"title":"A Study of Relationship Between Music Streaming Behavior and Big Five Personality Traits of Spotify Users","authors":"Thanit Hongpanarak, J. Mongkolnavin","doi":"10.1145/3468784.3469854","DOIUrl":"https://doi.org/10.1145/3468784.3469854","url":null,"abstract":"Personality Traits are important customer insights for business. Persuasive messages in advertising campaigns are more effective when customized to fit the customers' personalities. Researches suggested that music preference can reflect personality traits. However, those studies collected music listening history by using self-report of which the data obtained can be incomplete. This research aims to increase the completeness of music listening data by conducting a study on the three-month music streaming history of volunteers recorded automatically by Spotify. The eight audio features of each song (Acousticness, Danceability, Energy, Instrumentalness, Liveness, Speechiness, Valence, and Tempo) were extracted using Spotify's Application Programming Interface. The averages of these features calculated from songs in the music streaming history of each volunteer were used to represent his music preference. Pearson's Correlation method was employed to analyze relationships between the Big 5 Personality Traits and the music preference of 40 volunteers. The result shows a positive correlation between Openness-to-Experience and Liveness, a positive correlation between Extraversion and Acousticness, and a negative correlation between Extraversion with Energy and Speechiness. Agreeableness shows a positive correlation with Tempo. Instrumentalness is the only song feature that has a positive correlation with Neuroticism.","PeriodicalId":341589,"journal":{"name":"The 12th International Conference on Advances in Information Technology","volume":"71 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133097368","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：