Hiroki Nomiya
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Hiroki Nomiya has a total of 76 co-authors. Here are the top co-authors by number of shared publications:
Teruhisa Hochin
Graduate School of Information Science, Kyoto Institute of Technology, Kyoto, Japan
87 shared publications- Teruhisa Hochin
Kyoto Institute of Technology
31 shared publications Yuya Yokoyama
13 shared publications- Hideya Nakanishi
National Institute for Fusion Science, Toki, Japan
7 shared publications Shunsuke Akai
Kyoto Institute of Technology, Kyoto, Japan & Kanden System Solutions Co., Inc., Osaka, Japan
7 shared publicationsYui Nonomura
Graduate School of Information Science, Kyoto Institute of Technology, Kyoto, Japan
6 shared publications
Latest Publications
- Open Access
An Artificial Intelligence Model for Sensing Affective Valence and Arousal from Facial Images
Artificial intelligence (AI) models can sense subjective affective states from facial images. Although recent psychological studies have indicated that dimensional affective states of valence and arousal are systematically associated with facial expressions, no AI models have been developed to estimate these affective states from facial images based on empirical data. We developed a recurrent neural network-based AI model to estimate subjective valence and arousal states from facial images. We trained our model using a database containing participant valence/arousal states and facial images. Leave-one-out cross-validation supported the validity of the model for predicting subjective valence and arousal states. We further validated the effectiveness of the model by analyzing a dataset containing participant valence/arousal ratings and facial videos. The model predicted second-by-second valence and arousal states, with prediction performance comparable to that of FaceReader, a commercial AI model that estimates dimensional affective states based on a different approach. We constructed a graphical user interface to show real-time affective valence and arousal states by analyzing facial video data. Our model is the first distributable AI model for sensing affective valence and arousal from facial images/videos to be developed based on an empirical database; we anticipate that it will have many practical uses, such as in mental health monitoring and marketing research.
Open AccessAn Artificial Intelligence Model for Sensing Affective Valence and Arousal from Facial Images
Artificial intelligence (AI) models can sense subjective affective states from facial images. Although recent psychological studies have indicated that dimensional affective states of valence and arousal are systematically associated with facial expressions, no AI models have been developed to estimate these affective states from facial images based on empirical data. We developed a recurrent neural network-based AI model to estimate subjective valence and arousal states from facial images. We trained our model using a database containing participant valence/arousal states and facial images. Leave-one-out cross-validation supported the validity of the model for predicting subjective valence and arousal states. We further validated the effectiveness of the model by analyzing a dataset containing participant valence/arousal ratings and facial videos. The model predicted second-by-second valence and arousal states, with prediction performance comparable to that of FaceReader, a commercial AI model that estimates dimensional affective states based on a different approach. We constructed a graphical user interface to show real-time affective valence and arousal states by analyzing facial video data. Our model is the first distributable AI model for sensing affective valence and arousal from facial images/videos to be developed based on an empirical database; we anticipate that it will have many practical uses, such as in mental health monitoring and marketing research.
- 15 September 2023
- Published by Springer Nature
- p. 440-452
Two-Step Classification Method for Sadness and Fear Facial Expression Classification Using Facial Feature Points and FACS
- 15 September 2023
- Published by Springer Nature
- p. 440-452
Two-Step Classification Method for Sadness and Fear Facial Expression Classification Using Facial Feature Points and FACS
- Open Access
- 18 November 2022
- Published by Springer Nature in International Journal of Networked and Distributed Computing
- Vol. 10 (1-2) , 11-20
Application of 2‑gram and 3‑gram to Obtain Factor Scores of Statements Posted at Q&A Sites
With a view to solving the mismatches between the ideas of questioners and respondents of Question and Answer (Q&A) sites, impression evaluation experiments have resulted in obtaining nine factors of impressions. Then through multiple regression analysis factor scores have been estimated by utilizing the feature values of statements, such as syntactic information, etc. Those factor scores calculated were subsequently employed for inspecting their potential to detect respondents who are expected and likely to appropriately answer a newly posted question. Nevertheless, our method so far has largely depended on the syntactic information extracted through morphological analysis. Moreover, the number of explanatory variables utilized for obtaining factor scores has been appreciably extravagant and complex. Thus, instead of morphological analysis, 2-gram was applied to the explanatory variables to estimate factor scores. The analysis result with the application of 2-gram has led to greater estimation accuracy than the case of morphological analysis for all nine factors. For further perception and comparison, in this paper, 3-gram was applied to the feature values in place of 2-gram or morphological analysis, in a similar fashion as the previous analysis using 2-gram. Further analysis has shown that 2-gram and 3-gram outperform morphological analysis in terms of estimation accuracy. Comparing the results for the nine factors, 2-gram showed the best results. It could also be suggested that a mere 2-gram or 3-gram would be sufficient in applying N-gram as syntactic information of the feature values to estimate factor scores.
- 18 November 2022
- Published by Springer Nature in International Journal of Networked and Distributed Computing
- Vol. 10 (1-2) , 11-20
Open AccessApplication of 2‑gram and 3‑gram to Obtain Factor Scores of Statements Posted at Q&A Sites
With a view to solving the mismatches between the ideas of questioners and respondents of Question and Answer (Q&A) sites, impression evaluation experiments have resulted in obtaining nine factors of impressions. Then through multiple regression analysis factor scores have been estimated by utilizing the feature values of statements, such as syntactic information, etc. Those factor scores calculated were subsequently employed for inspecting their potential to detect respondents who are expected and likely to appropriately answer a newly posted question. Nevertheless, our method so far has largely depended on the syntactic information extracted through morphological analysis. Moreover, the number of explanatory variables utilized for obtaining factor scores has been appreciably extravagant and complex. Thus, instead of morphological analysis, 2-gram was applied to the explanatory variables to estimate factor scores. The analysis result with the application of 2-gram has led to greater estimation accuracy than the case of morphological analysis for all nine factors. For further perception and comparison, in this paper, 3-gram was applied to the feature values in place of 2-gram or morphological analysis, in a similar fashion as the previous analysis using 2-gram. Further analysis has shown that 2-gram and 3-gram outperform morphological analysis in terms of estimation accuracy. Comparing the results for the nine factors, 2-gram showed the best results. It could also be suggested that a mere 2-gram or 3-gram would be sufficient in applying N-gram as syntactic information of the feature values to estimate factor scores.
- Open Access
- 20 June 2021
- Published by Association for Computing Machinery (ACM)
- p. 32-38
Identification of Corresponding Numerical Attributes in Heterogeneous Databases Based on Instances
Identification of attributes in heterogeneous databases is widely known as the schema matching problem, and many studies have been published. Although existing studies using schema information have been proposed, schema information cannot always be used. In such a case, a schema matching method using instances is used as an alternative method, which is called instance-based schema matching. In this paper, we propose an instance-based schema matching method for the attributes storing numerical data. It uses data distributions and correlations between two attributes. The proposed method is experimentally evaluated by using several databases. As a result, the proposed method could find appropriate attribute correspondences.
- 20 June 2021
- Published by Association for Computing Machinery (ACM)
- p. 32-38
Open AccessIdentification of Corresponding Numerical Attributes in Heterogeneous Databases Based on Instances
Identification of attributes in heterogeneous databases is widely known as the schema matching problem, and many studies have been published. Although existing studies using schema information have been proposed, schema information cannot always be used. In such a case, a schema matching method using instances is used as an alternative method, which is called instance-based schema matching. In this paper, we propose an instance-based schema matching method for the attributes storing numerical data. It uses data distributions and correlations between two attributes. The proposed method is experimentally evaluated by using several databases. As a result, the proposed method could find appropriate attribute correspondences.
- Open Access
- 1 June 2021
- Published by Elsevier in Fusion Engineering and Design
- Vol. 167, 112360
Prediction of unusual plasma discharge by using Support Vector Machine
- 1 June 2021
- Published by Elsevier in Fusion Engineering and Design
- Vol. 167, 112360
Open AccessPrediction of unusual plasma discharge by using Support Vector Machine
- 1 April 2020
- Published by IGI Global Scientific Publishing in International Journal of Software Innovation
- Vol. 8 (2) , 1-22
Incremental Hierarchical Clustering for Data Insertion and Its Evaluation
Clustering is employed in various fields. However, the conventional method does not consider changing data. Therefore, if the data is changed, the entire dataset must be re-clustered. This article proposes a clustering method to update the clustering result obtained by a hierarchical clustering method without re-clustering when a point is inserted. This article defines the center and the radius of a cluster and determine the cluster to be inserted. The insertion location is determined by similarity based on the conventional clustering method. this research introduces the concept of outliers and consider creating a cluster caused by the insertion. By examining the multimodality of a cluster, the cluster is divided. In addition, when the number of clusters increases, data points previously inserted are updated by re-insertion. Compared with the conventional method, the experimental results demonstrate that the execution time of the proposed method is significantly smaller and clustering accuracy is comparable for some data.
- 1 April 2020
- Published by IGI Global Scientific Publishing in International Journal of Software Innovation
- Vol. 8 (2) , 1-22
Incremental Hierarchical Clustering for Data Insertion and Its Evaluation
Clustering is employed in various fields. However, the conventional method does not consider changing data. Therefore, if the data is changed, the entire dataset must be re-clustered. This article proposes a clustering method to update the clustering result obtained by a hierarchical clustering method without re-clustering when a point is inserted. This article defines the center and the radius of a cluster and determine the cluster to be inserted. The insertion location is determined by similarity based on the conventional clustering method. this research introduces the concept of outliers and consider creating a cluster caused by the insertion. By examining the multimodality of a cluster, the cluster is divided. In addition, when the number of clusters increases, data points previously inserted are updated by re-insertion. Compared with the conventional method, the experimental results demonstrate that the execution time of the proposed method is significantly smaller and clustering accuracy is comparable for some data.
- Open Access
- 1 January 2020
- Published by Japan Society of Kansei Engineering in International Symposium on Affective Science and Engineering
- Vol. ISASE2020, 1-4
Cultural and Gender Differences of Impression of Sound Clips
This paper experimentally clarifies similarities and differences of the impression of sound clips between Japanese and Chinese males, and those between Chinese males and females. Forty sound clips are evaluated through the SD method. It is shown that the factor of brightness commonly appears in the impression factors of Japanese males, Chinese males, and Chinese females, while the other factors do not always appear. The factors of Japanese males may be similar to those of Chinese females.
- 1 January 2020
- Published by Japan Society of Kansei Engineering in International Symposium on Affective Science and Engineering
- Vol. ISASE2020, 1-4
Open AccessCultural and Gender Differences of Impression of Sound Clips
This paper experimentally clarifies similarities and differences of the impression of sound clips between Japanese and Chinese males, and those between Chinese males and females. Forty sound clips are evaluated through the SD method. It is shown that the factor of brightness commonly appears in the impression factors of Japanese males, Chinese males, and Chinese females, while the other factors do not always appear. The factors of Japanese males may be similar to those of Chinese females.
- Open Access
- 1 January 2020
- Published by Japan Society of Kansei Engineering in International Journal of Affective Engineering
- Vol. 19 (2) , 101-110
Quantitative Evaluation to Investigate Further Tendency of Obtaining Potential Appropriate Respondents to Questions at Q&A Sites
In order to eliminate mismatches between the intentions of questioners and respondents of Question and Answer (Q&A) sites, nine factors of impressions for statements have experimentally been obtained. Factor scores have been then estimated by using the feature values of statements. So far the possibility of detecting respondents who can appropriately answer a newly posted question has been established for several categories e.g. Auction, PC, etc. It has been shown that the distance and the number of appearance could lead to selecting users who are able to appropriately answer a question. In order to inspect these tendencies, this paper tries to find the possibility of detecting appropriate respondents by adding respective eight question statements for each of the nine categories. As a result of analysis, the tendencies that particular several users are apt to appear in each category has been verified. Meanwhile, several different outstanding tendencies have been also observed.
- 1 January 2020
- Published by Japan Society of Kansei Engineering in International Journal of Affective Engineering
- Vol. 19 (2) , 101-110
Open AccessQuantitative Evaluation to Investigate Further Tendency of Obtaining Potential Appropriate Respondents to Questions at Q&A Sites
In order to eliminate mismatches between the intentions of questioners and respondents of Question and Answer (Q&A) sites, nine factors of impressions for statements have experimentally been obtained. Factor scores have been then estimated by using the feature values of statements. So far the possibility of detecting respondents who can appropriately answer a newly posted question has been established for several categories e.g. Auction, PC, etc. It has been shown that the distance and the number of appearance could lead to selecting users who are able to appropriately answer a question. In order to inspect these tendencies, this paper tries to find the possibility of detecting appropriate respondents by adding respective eight question statements for each of the nine categories. As a result of analysis, the tendencies that particular several users are apt to appear in each category has been verified. Meanwhile, several different outstanding tendencies have been also observed.
- 1 July 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 449-454
Improvement of Multi-Dimensional Indexing System for Multimedia Big Data
- 1 July 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 449-454
Improvement of Multi-Dimensional Indexing System for Multimedia Big Data
- 1 July 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. j96 d, 221-226
Extraction of Useful Features from Neural Network for Facial Expression Recognition
- 1 July 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. j96 d, 221-226
Extraction of Useful Features from Neural Network for Facial Expression Recognition