Ivan Marsic

Dr. Ivan Marsic

orcid

Research Focus & Metrics

Academic Career Length

20Years (2007-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 January 2018 in Proceedings of the conference. Association for Computational Linguistics. Meeting
Verified
Conference Paper
Open access
PDF file
YGYue Gu
Yue Gu
KYKangning Yang
Kangning Yang
SFShiyu Fu
Shiyu Fu
SCShuhong Chen
Shuhong Chen
XLXinyu Li
Xinyu Li
IMIvan Marsic
Ivan Marsic
Yue Gu, Kangning Yang, Shiyu Fu, Shuhong Chen, Xinyu Li, Ivan Marsic. Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2018.

14 November 2016
Verified
Conference Paper
Open access
XLXinyu Li
Xinyu Li
YZYanyi Zhang
Yanyi Zhang
IMIvan Marsic
Ivan Marsic
ASAleksandra Sarcevic
Aleksandra Sarcevic
RBRandall S. Burd
Randall S. Burd
We present a system for activity recognition from passive RFID data using a deep convolutional neural network. We directly feed the RFID data into a deep convolutional neural network for activity recognition instead of selecting features and using a cascade structure that first detects object use from RFID data followed by predicting the activity. Because our system treats activity recognition as a multi-class classification problem, it is scalable for applications with large number of activity classes. We tested our system using RFID data collected in a trauma room, including 14 hours of RFID data from 16 actual trauma resuscitations. Our system outperformed existing systems developed for activity recognition and achieved similar performance with process-phase detection as systems that require wearable sensors or manually-generated input. We also analyzed the strengths and limitations of our current deep learning architecture for activity recognition from RFID data.

13 September 2018 in International Conference on Acoustics, Speech, and Signal Processing (ICASSP)
Verified
Conference Paper
Closed access
YGYue Gu
Yue Gu
SCShuhong Chen
Shuhong Chen
IMIvan Marsic
Ivan Marsic
In this paper, we present a novel deep multimodal framework to predict human emotions based on sentence-level spoken language. Our architecture has two distinctive characteristics. First, it extracts the high-level features from both text and audio via a hybrid deep multimodal structure, which considers the spatial information from text, temporal information from audio, and high -level associations from low-level handcrafted features. Second, we fuse all features by using a three-layer deep neural network to learn the correlations across modalities and train the feature extraction and fusion modules together, allowing optimal global fine-tuning of the entire structure. We evaluated the proposed framework on the IEMOCAP dataset. Our result shows promising performance, achieving 60.4% in weighted accnrar-v for five emotion categories.

11 April 2017
Verified
Book Chapter
Closed access
PDF file
YGYue Gu
Yue Gu
XLXinyu Li
Xinyu Li
SCShuhong Chen
Shuhong Chen
JZJianyu Zhang
Jianyu Zhang
IMIvan Marsic
Ivan Marsic

1 May 2016
Verified
Conference Paper
Closed access
XLXinyu Li
Xinyu Li
DYDongyang Yao
Dongyang Yao
XPXuechao Pan
Xuechao Pan
JJJonathan Johannaman
Jonathan Johannaman
JYJaeWon Yang
JaeWon Yang
RBRandall S. Burd
Randall S. Burd
We describe a novel and practical activity recognition system for dynamic and complex medical settings using only passive RFID technology. Our activity recognition approach is based on the use of objects that are specific for a given activity. The object-use status is detected from RFID data and the activities are predicted from the statuses of use of different objects. We tagged 10 objects in a trauma room of an emergency department and recorded RFID data for 10 actual trauma resuscitations. More than 20,000 seconds of data were collected and used for analysis. The system achieved a 96% overall accuracy with a 0.74 F-score for detecting use of 10 common resuscitation objects and 95% accuracy with a 0.30 F Score for activity recognition of 10 medical activities.

1 September 2018 in Journal of Biomedical Informatics
Verified
Journal Article
Closed access
SYSen Yang
Sen Yang
ASAleksandra Sarcevic
Aleksandra Sarcevic
RFRichard A. Farneth
Richard A. Farneth
SCShuhong Chen
Shuhong Chen
OAOmar Z. Ahmed
Omar Z. Ahmed
RBRandall S. Burd
Randall S. Burd