The Experts below are selected from a list of 9390 Experts worldwide ranked by ideXlab platform
Miki Haseyama - One of the best experts on this subject based on the ideXlab platform.
-
emotion estimation via tensor based supervised decision level fusion from multiple Brodmann Areas
International Conference on Acoustics Speech and Signal Processing, 2017Co-Authors: Kento Sugata, Takahiro Ogawa, Miki HaseyamaAbstract:This paper presents a novel method that estimates human emotion based on tensor-based supervised decision-level fusion (TS-DLF) from multiple Brodmann Areas (BAs). From multiple brain data corresponding to these BAs captured by functional magnetic resonance imaging (fMRI), our method performs general tensor discriminant analysis (GTDA) to obtain features which can reflect the user's emotion. Furthermore, since the dimension of the obtained features becomes lower, this can avoid overfitting in the following training procedure of estimators. Next, by separately using the transformed BA data obtained after GTDA, we obtain multiple estimation results of the user's emotion based on logistic tensor regression (LTR). Then our method realizes the decision of the final result based on TS-DLF from the multiple estimation results. This approach, i.e., the integration of the multiple BAs' results for the whole-brain data, is the biggest contribution of this paper. TS-DLF successfully integrates the multiple estimation results with considering the performance of the LTR-based estimator constructed for each BA. Experimental results show that our method outperforms state-of-the-art approaches, and the effectiveness of our method can be confirmed.
-
ICASSP - Emotion estimation via tensor-based supervised decision-level fusion from multiple Brodmann Areas
2017 IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP), 2017Co-Authors: Kento Sugata, Takahiro Ogawa, Miki HaseyamaAbstract:This paper presents a novel method that estimates human emotion based on tensor-based supervised decision-level fusion (TS-DLF) from multiple Brodmann Areas (BAs). From multiple brain data corresponding to these BAs captured by functional magnetic resonance imaging (fMRI), our method performs general tensor discriminant analysis (GTDA) to obtain features which can reflect the user's emotion. Furthermore, since the dimension of the obtained features becomes lower, this can avoid overfitting in the following training procedure of estimators. Next, by separately using the transformed BA data obtained after GTDA, we obtain multiple estimation results of the user's emotion based on logistic tensor regression (LTR). Then our method realizes the decision of the final result based on TS-DLF from the multiple estimation results. This approach, i.e., the integration of the multiple BAs' results for the whole-brain data, is the biggest contribution of this paper. TS-DLF successfully integrates the multiple estimation results with considering the performance of the LTR-based estimator constructed for each BA. Experimental results show that our method outperforms state-of-the-art approaches, and the effectiveness of our method can be confirmed.
Darren Roddy - One of the best experts on this subject based on the ideXlab platform.
-
Papez's Forgotten Tract: 80 Years of Unreconciled Findings Concerning the Thalamocingulate Tract.
Frontiers in Neuroanatomy, 2019Co-Authors: Joshua Weininger, Elena Roman, Paul Tierney, Denis S. Barry, Hugh Gallagher, Kirk J. Levins, Erik O'hanlon, Veronica O'keane, Paul Murphy, Darren RoddyAbstract:The thalamocingulate tract is a key component of the Papez circuit that connects the anterior thalamic nucleus to the cingulum bundle. While the other white matter connections, consisting of the fornix, cingulum bundle and mammillothalamic tract, were well defined in Papez's original 1937 paper, the anatomy of the thalamocingulate pathway was mentioned only in passing. Subsequent research has been unable to clarify the precise anatomical trajectory of this tract. In particular, the site of thalamocingulate tract interactions with the cingulum bundle have been inconsistently reported. This review aims to synthesize research on this least studied component of the Papez circuit. A systemic approach to reviewing historical anatomical dissection and neuronal tracing studies as well as contemporary diffusion magnetic resonance imaging studies of the thalamocingulate tract was undertaken across species. We found that although inconsistent, prior research broadly encompasses two differing descriptions of how the anterior thalamic nucleus interfaces with the cingulum after passing laterally through the anterior limb of the internal capsule. The first group of studies show that the pathway turns medially and rostrally and passes to the anterior cingulate region (Brodmann Areas 24, 33, and 32) only. A second group suggests that the thalamocingulate tract interfaces with both the anterior and posterior cingulate (Brodmann Areas 23 and 31) and retrosplenial region (Brodmann area 29). We discuss potential reasons for these discrepancies such as altering methodologies and species differences. We also discuss how these inconsistencies may be resolved in further research with refinements of terminology for the cingulate cortex and the thalamocingulate tract. Understanding the precise anatomical course of the last remaining unresolved final white matter tract in the Papez circuit may facilitate accurate investigation of the role of the complete Papez circuit in emotion and memory.
Kento Sugata - One of the best experts on this subject based on the ideXlab platform.
-
emotion estimation via tensor based supervised decision level fusion from multiple Brodmann Areas
International Conference on Acoustics Speech and Signal Processing, 2017Co-Authors: Kento Sugata, Takahiro Ogawa, Miki HaseyamaAbstract:This paper presents a novel method that estimates human emotion based on tensor-based supervised decision-level fusion (TS-DLF) from multiple Brodmann Areas (BAs). From multiple brain data corresponding to these BAs captured by functional magnetic resonance imaging (fMRI), our method performs general tensor discriminant analysis (GTDA) to obtain features which can reflect the user's emotion. Furthermore, since the dimension of the obtained features becomes lower, this can avoid overfitting in the following training procedure of estimators. Next, by separately using the transformed BA data obtained after GTDA, we obtain multiple estimation results of the user's emotion based on logistic tensor regression (LTR). Then our method realizes the decision of the final result based on TS-DLF from the multiple estimation results. This approach, i.e., the integration of the multiple BAs' results for the whole-brain data, is the biggest contribution of this paper. TS-DLF successfully integrates the multiple estimation results with considering the performance of the LTR-based estimator constructed for each BA. Experimental results show that our method outperforms state-of-the-art approaches, and the effectiveness of our method can be confirmed.
-
ICASSP - Emotion estimation via tensor-based supervised decision-level fusion from multiple Brodmann Areas
2017 IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP), 2017Co-Authors: Kento Sugata, Takahiro Ogawa, Miki HaseyamaAbstract:This paper presents a novel method that estimates human emotion based on tensor-based supervised decision-level fusion (TS-DLF) from multiple Brodmann Areas (BAs). From multiple brain data corresponding to these BAs captured by functional magnetic resonance imaging (fMRI), our method performs general tensor discriminant analysis (GTDA) to obtain features which can reflect the user's emotion. Furthermore, since the dimension of the obtained features becomes lower, this can avoid overfitting in the following training procedure of estimators. Next, by separately using the transformed BA data obtained after GTDA, we obtain multiple estimation results of the user's emotion based on logistic tensor regression (LTR). Then our method realizes the decision of the final result based on TS-DLF from the multiple estimation results. This approach, i.e., the integration of the multiple BAs' results for the whole-brain data, is the biggest contribution of this paper. TS-DLF successfully integrates the multiple estimation results with considering the performance of the LTR-based estimator constructed for each BA. Experimental results show that our method outperforms state-of-the-art approaches, and the effectiveness of our method can be confirmed.
Joshua Weininger - One of the best experts on this subject based on the ideXlab platform.
-
Papez's Forgotten Tract: 80 Years of Unreconciled Findings Concerning the Thalamocingulate Tract.
Frontiers in Neuroanatomy, 2019Co-Authors: Joshua Weininger, Elena Roman, Paul Tierney, Denis S. Barry, Hugh Gallagher, Kirk J. Levins, Erik O'hanlon, Veronica O'keane, Paul Murphy, Darren RoddyAbstract:The thalamocingulate tract is a key component of the Papez circuit that connects the anterior thalamic nucleus to the cingulum bundle. While the other white matter connections, consisting of the fornix, cingulum bundle and mammillothalamic tract, were well defined in Papez's original 1937 paper, the anatomy of the thalamocingulate pathway was mentioned only in passing. Subsequent research has been unable to clarify the precise anatomical trajectory of this tract. In particular, the site of thalamocingulate tract interactions with the cingulum bundle have been inconsistently reported. This review aims to synthesize research on this least studied component of the Papez circuit. A systemic approach to reviewing historical anatomical dissection and neuronal tracing studies as well as contemporary diffusion magnetic resonance imaging studies of the thalamocingulate tract was undertaken across species. We found that although inconsistent, prior research broadly encompasses two differing descriptions of how the anterior thalamic nucleus interfaces with the cingulum after passing laterally through the anterior limb of the internal capsule. The first group of studies show that the pathway turns medially and rostrally and passes to the anterior cingulate region (Brodmann Areas 24, 33, and 32) only. A second group suggests that the thalamocingulate tract interfaces with both the anterior and posterior cingulate (Brodmann Areas 23 and 31) and retrosplenial region (Brodmann area 29). We discuss potential reasons for these discrepancies such as altering methodologies and species differences. We also discuss how these inconsistencies may be resolved in further research with refinements of terminology for the cingulate cortex and the thalamocingulate tract. Understanding the precise anatomical course of the last remaining unresolved final white matter tract in the Papez circuit may facilitate accurate investigation of the role of the complete Papez circuit in emotion and memory.
-
Papez’s Forgotten Tract: 80 Years of Unreconciled Findings Concerning the Thalamocingulate Tract
Frontiers Media S.A., 2019Co-Authors: Joshua Weininger, Elena Roman, Paul Tierney, Hugh Gallagher, Kirk J. Levins, Paul Murphy, Denis Barry, Veronica O’keane, Erik O’hanlon, Darren W. RoddyAbstract:The thalamocingulate tract is a key component of the Papez circuit that connects the anterior thalamic nucleus (ATN) to the cingulum bundle. While the other white matter connections, consisting of the fornix, cingulum bundle and mammillothalamic tract, were well defined in Papez’s original 1937 paper, the anatomy of the thalamocingulate pathway was mentioned only in passing. Subsequent research has been unable to clarify the precise anatomical trajectory of this tract. In particular, the site of thalamocingulate tract interactions with the cingulum bundle have been inconsistently reported. This review aims to synthesize research on this least studied component of the Papez circuit. A systemic approach to reviewing historical anatomical dissection and neuronal tracing studies as well as contemporary diffusion magnetic resonance imaging studies of the thalamocingulate tract was undertaken across species. We found that although inconsistent, prior research broadly encompasses two differing descriptions of how the ATN interfaces with the cingulum after passing laterally through the anterior limb of the internal capsule. The first group of studies show that the pathway turns medially and rostrally and passes to the anterior cingulate region (Brodmann Areas 24, 33, and 32) only. A second group suggests that the thalamocingulate tract interfaces with both the anterior and posterior cingulate (Brodmann Areas 23 and 31) and retrosplenial region (Brodmann area 29). We discuss potential reasons for these discrepancies such as altering methodologies and species differences. We also discuss how these inconsistencies may be resolved in further research with refinements of terminology for the cingulate cortex and the thalamocingulate tract. Understanding the precise anatomical course of the last remaining unresolved final white matter tract in the Papez circuit may facilitate accurate investigation of the role of the complete Papez circuit in emotion and memory
Takahiro Ogawa - One of the best experts on this subject based on the ideXlab platform.
-
emotion estimation via tensor based supervised decision level fusion from multiple Brodmann Areas
International Conference on Acoustics Speech and Signal Processing, 2017Co-Authors: Kento Sugata, Takahiro Ogawa, Miki HaseyamaAbstract:This paper presents a novel method that estimates human emotion based on tensor-based supervised decision-level fusion (TS-DLF) from multiple Brodmann Areas (BAs). From multiple brain data corresponding to these BAs captured by functional magnetic resonance imaging (fMRI), our method performs general tensor discriminant analysis (GTDA) to obtain features which can reflect the user's emotion. Furthermore, since the dimension of the obtained features becomes lower, this can avoid overfitting in the following training procedure of estimators. Next, by separately using the transformed BA data obtained after GTDA, we obtain multiple estimation results of the user's emotion based on logistic tensor regression (LTR). Then our method realizes the decision of the final result based on TS-DLF from the multiple estimation results. This approach, i.e., the integration of the multiple BAs' results for the whole-brain data, is the biggest contribution of this paper. TS-DLF successfully integrates the multiple estimation results with considering the performance of the LTR-based estimator constructed for each BA. Experimental results show that our method outperforms state-of-the-art approaches, and the effectiveness of our method can be confirmed.
-
ICASSP - Emotion estimation via tensor-based supervised decision-level fusion from multiple Brodmann Areas
2017 IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP), 2017Co-Authors: Kento Sugata, Takahiro Ogawa, Miki HaseyamaAbstract:This paper presents a novel method that estimates human emotion based on tensor-based supervised decision-level fusion (TS-DLF) from multiple Brodmann Areas (BAs). From multiple brain data corresponding to these BAs captured by functional magnetic resonance imaging (fMRI), our method performs general tensor discriminant analysis (GTDA) to obtain features which can reflect the user's emotion. Furthermore, since the dimension of the obtained features becomes lower, this can avoid overfitting in the following training procedure of estimators. Next, by separately using the transformed BA data obtained after GTDA, we obtain multiple estimation results of the user's emotion based on logistic tensor regression (LTR). Then our method realizes the decision of the final result based on TS-DLF from the multiple estimation results. This approach, i.e., the integration of the multiple BAs' results for the whole-brain data, is the biggest contribution of this paper. TS-DLF successfully integrates the multiple estimation results with considering the performance of the LTR-based estimator constructed for each BA. Experimental results show that our method outperforms state-of-the-art approaches, and the effectiveness of our method can be confirmed.
