Debarati Bhattacharjee
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
Debarati Bhattacharjee has a total of 5 co-authors. Here are the top co-authors by number of shared publications:
- Arpan Dam
Computer Science and Engineering, IIT Kharagpur, Kharagpur, West Bengal, India
1 shared publication - Bivas Mitra
IIT Kharagpur
1 shared publication Munesh Singh
Indian Institute of Information Technology Design and Manufacturing Kancheepuram
1 shared publication- Sayan Pathak
Microsoft Redmond, USA, Redmond, Washington, US
1 shared publication - Suryansh Kumar
Computer Science and Engineering, IIT Kharagpur, Kharagpur, West Bengal, India
1 shared publication
Latest Publications
- Open Access
- 27 March 2023
- Published by Association for Computing Machinery (ACM)
- p. 1623-1632
Topic Aware Influential Member Detection in Meetup
Hosting popular Meetup events is one of the primary objectives of the Meetup organizers. This paper explores the possibility of inviting a few key influential members to attend Meetup events, who may further influence their followers to attend and boost the popularity of those Meetup events. Importantly, our pilot study reveals that topics of the Meetup events play a key role behind the effectiveness of the influential members. Leveraging this observation, in this paper, we develop Topic Aware Influencer Detection (TAID) heuristics, which recommends (i) top-k influential members Ik, and (ii) top-b influence badges Rb based on the topical interest of a Meetup group. This indicates that Ik. will be most effective in influencing the Meetup members to attend the events hosted on topic Rb. TAID heuristics contains two major blocks (a) influence propagation graph construction, and (b) recommendation generation. Rigorous evaluation of TAID on 1447 Meetup groups with three different topics reveals that TAID comfortably outperforms the baselines by influencing (on average) 15% more Meetup members.
- 27 March 2023
- Published by Association for Computing Machinery (ACM)
- p. 1623-1632
Open AccessTopic Aware Influential Member Detection in Meetup
Hosting popular Meetup events is one of the primary objectives of the Meetup organizers. This paper explores the possibility of inviting a few key influential members to attend Meetup events, who may further influence their followers to attend and boost the popularity of those Meetup events. Importantly, our pilot study reveals that topics of the Meetup events play a key role behind the effectiveness of the influential members. Leveraging this observation, in this paper, we develop Topic Aware Influencer Detection (TAID) heuristics, which recommends (i) top-k influential members Ik, and (ii) top-b influence badges Rb based on the topical interest of a Meetup group. This indicates that Ik. will be most effective in influencing the Meetup members to attend the events hosted on topic Rb. TAID heuristics contains two major blocks (a) influence propagation graph construction, and (b) recommendation generation. Rigorous evaluation of TAID on 1447 Meetup groups with three different topics reveals that TAID comfortably outperforms the baselines by influencing (on average) 15% more Meetup members.
- Open Access
- 23 July 2021
- Published by Springer Nature in Research Square
Time-domain Feature and Ensemble Model based Classification of EMG Signals for Hand Gesture Recognition
The electromyography (EMG) signal is the electrical current generated in muscles due to the inter-change of ions during their contractions. It has many applications in clinical diagnostics and the biomedical field. This paper has experimented with various ensemble algorithms and time-domain features to classify eight types of hand gestures. To train and test the machine learning models, we have extracted eight types of time-domain features from the raw EMG signals, such as integrated EMG (IEMG), variance, mean absolute value (MAV), modified mean absolute value type 1, waveform length, root mean square, average amplitude change, and difference absolute standard deviation value. The ensemble machine learning models are based on stacking, bagging, and gradient boosting. We have used four different-sized training sets to evaluate the performance of these classifiers. From the performance evaluation, we have identified the XG-Boost (gblinear) classifier with the IEMG feature as the best classifier-feature pair. The proposed classifier-feature pair has given better performance with a classification accuracy of 98.33% and a processing time of 5.67 μs for one vector than the existing extended associative memory-MAV classifier-feature pair.
- 23 July 2021
- Published by Springer Nature in Research Square
Open AccessTime-domain Feature and Ensemble Model based Classification of EMG Signals for Hand Gesture Recognition
The electromyography (EMG) signal is the electrical current generated in muscles due to the inter-change of ions during their contractions. It has many applications in clinical diagnostics and the biomedical field. This paper has experimented with various ensemble algorithms and time-domain features to classify eight types of hand gestures. To train and test the machine learning models, we have extracted eight types of time-domain features from the raw EMG signals, such as integrated EMG (IEMG), variance, mean absolute value (MAV), modified mean absolute value type 1, waveform length, root mean square, average amplitude change, and difference absolute standard deviation value. The ensemble machine learning models are based on stacking, bagging, and gradient boosting. We have used four different-sized training sets to evaluate the performance of these classifiers. From the performance evaluation, we have identified the XG-Boost (gblinear) classifier with the IEMG feature as the best classifier-feature pair. The proposed classifier-feature pair has given better performance with a classification accuracy of 98.33% and a processing time of 5.67 μs for one vector than the existing extended associative memory-MAV classifier-feature pair.